{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":197,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":197,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"b6678b49f8d8","filters":{"topic":"Customer churn and segmentation"}},"results":[{"id":"W2093015399","doi":"10.1002/dir.20027","title":"Can we predict customer lifetime value?","year":2005,"lang":"en","type":"article","venue":"Journal of Interactive Marketing","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":246,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Profitability index; Customer lifetime value; Profit (economics); Customer profitability; Customer value; Marketing; Sample (material); Value (mathematics); Business; Econometrics; Computer science; Microeconomics; Customer retention; Economics; Finance","authors":[{"name":"Edward C. Malthouse","is_ca":false},{"name":"Robert C. Blattberg","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01001644444592861,"gpt":0.2453457079815457,"spread":0.2353292635356171,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004517358,0.0007878469,0.0007964984,0.002305868,0.0004636406,0.003018882,0.001323615,0.002246195,0.003169585],"category_scores_gemma":[0.05018074,0.0003217287,0.0004804298,0.002699961,0.001090363,0.008630835,0.0007147708,0.002618238,0.001529674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001211234,"about_ca_system_score_gemma":0.0006345166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01081545,"about_ca_topic_score_gemma":0.009071791,"domain_scores_codex":[0.9987862,0.0005716484,0.00005832638,0.0001850849,0.0002280699,0.0001706107],"domain_scores_gemma":[0.9771332,0.01604168,0.002744131,0.001385106,0.001977831,0.0007180976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002941563,0.0002315408,0.7583166,0.0001081893,0.0002544582,0.0001306787,0.0005211851,0.06127756,0.0001169485,0.01074399,0.01038324,0.1576214],"study_design_scores_gemma":[0.0000602316,0.0004101833,0.2839758,0.0002814094,0.0001787535,0.0005090754,0.001471063,0.5629274,0.0006689177,0.1406156,0.008756433,0.0001451314],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9073489,0.006152094,0.04266683,0.02497282,0.0003614792,0.00008524166,0.003648219,0.0003612302,0.01440324],"genre_scores_gemma":[0.9937212,0.0008362295,0.003025841,0.0003627702,0.0001581315,0.00002313856,0.00108619,0.00001851458,0.0007679844],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01081545,"threshold_uncertainty_score":0.02389038,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1965798541","doi":"10.1145/1167838.1167842","title":"Current trends in web data analysis","year":2006,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":81,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Current (fluid); Computer science; Data science; Geology; Oceanography","authors":[{"name":"Arun Sen","is_ca":false},{"name":"Peter A. Dacin","is_ca":true},{"name":"Christos Pattichis","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09939293288559362,"gpt":0.3399127552088232,"spread":0.2405198223232296,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03244618,0.001224175,0.002139298,0.01704052,0.00168836,0.0141245,0.004100718,0.002984564,0.00699503],"category_scores_gemma":[0.08158712,0.001260545,0.001545496,0.02465571,0.003925242,0.02092784,0.002687278,0.005079608,0.004451221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00498132,"about_ca_system_score_gemma":0.005675593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0106855,"about_ca_topic_score_gemma":0.01550459,"domain_scores_codex":[0.9754684,0.006438754,0.002792717,0.005736637,0.00873227,0.0008311628],"domain_scores_gemma":[0.7466351,0.166722,0.01225348,0.009582385,0.05917174,0.005635282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004360139,0.0003861843,0.07729369,0.005495279,0.0002488072,0.0001071286,0.00126232,0.002656074,0.003687834,0.03258485,0.06149662,0.8143452],"study_design_scores_gemma":[0.00009142463,0.0003248851,0.108734,0.005474988,0.0003616555,0.002262462,0.0112419,0.06045721,0.009446728,0.0708409,0.7303209,0.0004428452],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.08898673,0.4224415,0.2218039,0.1951252,0.005039268,0.000574654,0.01059584,0.007732233,0.04770055],"genre_scores_gemma":[0.3646289,0.3093775,0.2525121,0.02508124,0.01227852,0.0009202482,0.01672276,0.002327645,0.01615125],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.03244618,"threshold_uncertainty_score":0.1715938,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080524058","doi":"10.1108/10878570010379392","title":"Measuring customer capital","year":2000,"lang":"en","type":"article","venue":"Strategy and Leadership","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Centre for Disability Prevention and Rehabilitation","funders":"","keywords":"Business; Customer retention; Customer advocacy; Customer to customer; Customer intelligence; Customer equity; Industrial organization; Voice of the customer; Marketing; Competitive advantage; Process management; Service quality","authors":[{"name":"Jan Duffy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1524170645425348,"gpt":0.2387043087124373,"spread":0.08628724416990255,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001447212,0.0005285041,0.0002554909,0.002970113,0.000559684,0.002464645,0.0006036127,0.000553114,0.006738906],"category_scores_gemma":[0.01059156,0.0001076427,0.0001764764,0.002446477,0.0003916716,0.001619016,0.0009586214,0.0005527233,0.001557381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001272477,"about_ca_system_score_gemma":0.0007696307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002845274,"about_ca_topic_score_gemma":0.002526294,"domain_scores_codex":[0.9963594,0.0007449558,0.0002522716,0.0002047237,0.002115117,0.000323507],"domain_scores_gemma":[0.9904041,0.003209521,0.001963945,0.0004748261,0.00312687,0.0008207985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002669743,0.0005124418,0.5313608,0.0003878449,0.0001646014,0.000166985,0.001051861,0.005146776,0.003243752,0.02182143,0.03008934,0.4057872],"study_design_scores_gemma":[0.0000443862,0.001614805,0.8464478,0.0006345846,0.0002435105,0.001077331,0.003842614,0.01577844,0.02036246,0.02352961,0.08624944,0.0001748224],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6999722,0.003349923,0.01526908,0.00172339,0.0003367364,0.0005341599,0.006022552,0.0002426778,0.2725493],"genre_scores_gemma":[0.9881337,0.0005841829,0.003058896,0.0001526906,0.00006607256,0.0001108203,0.001520182,0.000008003656,0.006365458],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006738906,"threshold_uncertainty_score":0.02254385,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042206577","doi":"10.1080/01969722.2015.1012892","title":"Uplift Random Forests","year":2015,"lang":"en","type":"article","venue":"Cybernetics & Systems","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":72,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Outcome (game theory); Random forest; Machine learning; Observational study; Artificial intelligence; Action (physics); Simple (philosophy); Range (aeronautics); Data mining; Statistics; Mathematics","authors":[{"name":"Leo Guelman","is_ca":false},{"name":"Montserrat Guillén","is_ca":false},{"name":"Ana María Pérez Marín","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03610241145063336,"gpt":0.2406608925201367,"spread":0.2045584810695033,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004414388,0.001196492,0.001808006,0.001850842,0.0007947815,0.00112704,0.001869692,0.001485988,0.003628656],"category_scores_gemma":[0.008143941,0.0006309899,0.001961459,0.001460611,0.0004842219,0.00117387,0.0009396457,0.001629876,0.001983957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000578146,"about_ca_system_score_gemma":0.001082659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00610239,"about_ca_topic_score_gemma":0.01439531,"domain_scores_codex":[0.9979335,0.001005649,0.00008883457,0.0004422784,0.0003465058,0.0001831651],"domain_scores_gemma":[0.9953402,0.003141352,0.0002960118,0.0006041676,0.0005094748,0.0001087453],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003845485,0.000261654,0.006204402,0.0002685556,0.0003629081,0.0002790808,0.00008958171,0.6482788,0.001407141,0.01730286,0.02595159,0.2992089],"study_design_scores_gemma":[0.0000332743,0.00003697439,0.0004381509,0.00002057521,0.0000288617,0.00005703232,0.00001250382,0.9818657,0.0004069254,0.01432132,0.002767178,0.0000114505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03014512,0.001204479,0.9578324,0.0004838143,0.0002645636,0.0003381307,0.002294606,0.004205907,0.003230958],"genre_scores_gemma":[0.446494,0.0007561184,0.5382137,0.0006334782,0.0004449862,0.0006482114,0.007076247,0.0004640592,0.005269241],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00610239,"threshold_uncertainty_score":0.02334583,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1519318168","doi":"10.5539/ibr.v8n6p224","title":"Customer Churn in Mobile Markets: A Comparison of Techniques","year":2015,"lang":"en","type":"article","venue":"International Business Research","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":63,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Decision tree; Logistic regression; Customer retention; Tree (set theory); Voice of the customer; Customer lifetime value; Customer needs","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.1116576909122309,"gpt":0.4132801804004889,"spread":0.301622489488258,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002704998,0.0005120209,0.0006485179,0.003245379,0.0005372661,0.001402695,0.001118748,0.0009719136,0.001979416],"category_scores_gemma":[0.007791742,0.0002551621,0.0007462071,0.00317368,0.0003676684,0.001785283,0.000885218,0.0005962268,0.0004708644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008288899,"about_ca_system_score_gemma":0.0007220453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004133397,"about_ca_topic_score_gemma":0.00509286,"domain_scores_codex":[0.9977938,0.0009481159,0.00009495858,0.0002282605,0.0007420777,0.0001928076],"domain_scores_gemma":[0.9894876,0.008294391,0.0006381161,0.0002589318,0.001125271,0.0001956312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001556646,0.0006078504,0.0651116,0.001228177,0.0003858848,0.0004154904,0.003183264,0.02770996,0.002776078,0.006756689,0.002898776,0.8873696],"study_design_scores_gemma":[0.0002708952,0.003508559,0.1879655,0.0008514177,0.0007583163,0.002496976,0.01331284,0.7447823,0.008087773,0.01621127,0.02148816,0.0002658137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8219818,0.01422724,0.1325604,0.00102918,0.0001531281,0.0004257477,0.000475585,0.0008930967,0.0282538],"genre_scores_gemma":[0.9327139,0.004021898,0.06055972,0.00009963213,0.00006800582,0.0001183262,0.0002630608,0.00007711142,0.002078185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004133397,"threshold_uncertainty_score":0.01430553,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2057292389","doi":"10.1007/s10479-008-0400-8","title":"ADTreesLogit model for customer churn prediction","year":2008,"lang":"en","type":"article","venue":"Annals of Operations Research","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":45,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Interpretability; Computer science; Tournament; Predictive modelling; CONTEST; Machine learning; Logistic regression; Artificial intelligence; Predictive analytics; Data mining; Mathematics","authors":[{"name":"Jiayin Qi","is_ca":false},{"name":"Li Zhang","is_ca":false},{"name":"Yan Liu","is_ca":false},{"name":"Ling Li","is_ca":false},{"name":"Yong‐Pin Zhou","is_ca":false},{"name":"Yao Shen","is_ca":false},{"name":"Liang Liang","is_ca":false},{"name":"LI Huai-zu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4472177535679772,"gpt":0.4369719839560914,"spread":0.01024576961188572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003121207,0.001199217,0.001865041,0.001430435,0.001284933,0.001760487,0.003021204,0.002424039,0.01035937],"category_scores_gemma":[0.006280265,0.001023134,0.001217104,0.002012624,0.0007382238,0.002853242,0.001086744,0.003610781,0.002809532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001799015,"about_ca_system_score_gemma":0.001808573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02657054,"about_ca_topic_score_gemma":0.03564094,"domain_scores_codex":[0.9991282,0.0004307673,0.00005007982,0.0001719664,0.0001042981,0.0001147529],"domain_scores_gemma":[0.9941096,0.004541791,0.000229072,0.0003396501,0.0006167541,0.0001631675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005473936,0.0003228479,0.005616809,0.0001140207,0.0001117913,0.00011994,0.00008085359,0.8788134,0.0003302783,0.01265477,0.01016659,0.09112131],"study_design_scores_gemma":[0.00001186809,0.00001507459,0.0002025603,0.000005095626,0.000009074923,0.000006577887,0.000005600812,0.9945837,0.00007994012,0.004621037,0.0004542315,0.000005249308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2691292,0.003627487,0.6990104,0.004523357,0.0006170642,0.0001678875,0.01033159,0.004652892,0.007940315],"genre_scores_gemma":[0.8874673,0.001109823,0.07543097,0.000615949,0.0003895561,0.0003731074,0.008595943,0.0003112394,0.02570608],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02657054,"threshold_uncertainty_score":0.05283177,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2588202084","doi":"10.1109/ssci.2016.7849921","title":"Customer shopping pattern prediction: A recurrent neural network approach","year":2016,"lang":"en","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Loyalty; Artificial neural network; Loyalty business model; Recurrent neural network; Customer relationship management; Recommender system; Customer intelligence; Customer retention; Service (business); Artificial intelligence; Service quality; Machine learning; Marketing; Business; Database","authors":[{"name":"Hojjat Salehinejad","is_ca":true},{"name":"Shahryar Rahnamayan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02881785416027927,"gpt":0.223965844183213,"spread":0.1951479900229338,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005932955,0.0005253472,0.0006292714,0.0006872169,0.0002270938,0.0005856019,0.0009516512,0.0007458705,0.0009837234],"category_scores_gemma":[0.001522501,0.0003245048,0.0006146254,0.0007013057,0.0001832477,0.0007053867,0.00034478,0.0008451206,0.0003247704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005369006,"about_ca_system_score_gemma":0.0004082875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01729237,"about_ca_topic_score_gemma":0.01452515,"domain_scores_codex":[0.9997581,0.00005952959,0.00001785944,0.00007029052,0.00004829854,0.00004597301],"domain_scores_gemma":[0.9995795,0.0001968387,0.00005740637,0.00002830327,0.0001183753,0.00001959861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002244667,0.0002787904,0.01068935,0.00007675618,0.0002638201,0.0002103289,0.0001125027,0.7820874,0.003492894,0.00328341,0.002905379,0.1963748],"study_design_scores_gemma":[0.000001152314,0.000006900925,0.0003484892,0.00000159914,0.000006449888,0.000005218494,0.000002068197,0.9991285,0.0001091461,0.0003330828,0.00005515774,0.000002174668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3042561,0.001534365,0.6858065,0.0009611181,0.0001444388,0.00007671984,0.000664803,0.001536689,0.005019321],"genre_scores_gemma":[0.9567656,0.0004224077,0.03902495,0.0001157128,0.00006978456,0.00005282057,0.0005550926,0.00003564046,0.002957922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01729237,"threshold_uncertainty_score":0.03438348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4327522692","doi":"10.1109/access.2023.3257352","title":"Development of a Customer Churn Model for Banking Industry Based on Hard and Soft Data Fusion","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Banking industry; Fusion; Data modeling; Sensor fusion; Business; Artificial intelligence; Finance; Database","authors":[{"name":"Masoud Alizadeh","is_ca":false},{"name":"Danial Sadrian Zadeh","is_ca":false},{"name":"Behzad Moshiri","is_ca":true},{"name":"Allahyar Montazeri","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.178961144832458,"gpt":0.3436977908249927,"spread":0.1647366459925347,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001485151,0.0006819668,0.001009786,0.00115015,0.0005428932,0.001602791,0.001762176,0.001540392,0.002055102],"category_scores_gemma":[0.002747771,0.0005616904,0.001067181,0.001333654,0.000740156,0.001888859,0.00104735,0.001647678,0.0005879421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001749199,"about_ca_system_score_gemma":0.001394481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01794552,"about_ca_topic_score_gemma":0.009808973,"domain_scores_codex":[0.9992761,0.0001528715,0.00005496906,0.0001895833,0.0001894445,0.0001371679],"domain_scores_gemma":[0.9988901,0.0005644968,0.0001584717,0.00004350198,0.0002858053,0.00005764681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008569894,0.0000794658,0.003760209,0.0000657666,0.00004813432,0.000185561,0.000173385,0.9523193,0.001322596,0.01288296,0.001091807,0.02798519],"study_design_scores_gemma":[9.934366e-7,0.000005622301,0.0001412403,0.000002111587,0.000003710504,0.000008564184,0.000004441603,0.9987766,0.00005412333,0.0009098616,0.00009000846,0.000002663988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07030178,0.0006753193,0.9205706,0.0006903896,0.00006236089,0.0001167363,0.0002792591,0.0005923213,0.006711307],"genre_scores_gemma":[0.9394551,0.0006457065,0.05325421,0.0001638465,0.00006793408,0.0002090941,0.0004192465,0.0000684558,0.005716258],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01794552,"threshold_uncertainty_score":0.03568214,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318769934","doi":"10.1007/s10799-023-00388-w","title":"The state of lead scoring models and their impact on sales performance","year":2023,"lang":"en","type":"article","venue":"Information Technology and Management","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":32,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Mitacs","keywords":"Lead (geology); Computer science; Lead time; Predictive modelling; Process (computing); Machine learning; Quality (philosophy); Artificial intelligence; Risk analysis (engineering); Data mining; Operations management; Engineering; Business","authors":[{"name":"Migao Wu","is_ca":true},{"name":"Pavel A. Andreev","is_ca":true},{"name":"Morad Benyoucef","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01519373876254896,"gpt":0.2288328260285474,"spread":0.2136390872659985,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02764266,0.0009637273,0.0009947418,0.002927006,0.001279979,0.008679735,0.001864522,0.002185808,0.003504073],"category_scores_gemma":[0.1165123,0.0006645574,0.0007440037,0.004096743,0.001695821,0.003993177,0.001189785,0.002735588,0.001144661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003843114,"about_ca_system_score_gemma":0.002856465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01193521,"about_ca_topic_score_gemma":0.01492806,"domain_scores_codex":[0.9845669,0.009771191,0.0005837839,0.001285102,0.003037387,0.0007556581],"domain_scores_gemma":[0.820198,0.1452945,0.006881334,0.008241142,0.01732625,0.002058787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.001900784,0.000868752,0.09473865,0.0002030423,0.0002513198,0.00004636902,0.0004007178,0.4906311,0.0009114095,0.0305961,0.006673065,0.3727786],"study_design_scores_gemma":[0.00005938848,0.0004518576,0.01124743,0.0001191382,0.0001151727,0.00005425622,0.0002452621,0.9688781,0.001896269,0.01493038,0.001929924,0.00007282892],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8323965,0.01286685,0.1218793,0.006408895,0.0004519583,0.00007963412,0.001054594,0.00183516,0.02302704],"genre_scores_gemma":[0.9858972,0.001164926,0.01007977,0.0001354305,0.0001286735,0.00001666337,0.0003650038,0.0001213015,0.002091056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02764266,"threshold_uncertainty_score":0.1461902,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4293791119","doi":"10.3390/app12168270","title":"Intelligent Decision Forest Models for Customer Churn Prediction","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Computer science; Random forest; Decision tree; Benchmark (surveying); Incentive; Software deployment; Robustness (evolution); Machine learning; Artificial intelligence; Majority rule; Scalability; Data mining; Operations research; Database; Engineering","authors":[{"name":"Fatima Enehezei Usman-Hamza","is_ca":false},{"name":"Abdullateef Oluwagbemiga Balogun","is_ca":false},{"name":"Luiz Fernando Capretz","is_ca":true},{"name":"Hammed A. Mojeed","is_ca":false},{"name":"Saipunidzam Mahamad","is_ca":false},{"name":"Shakirat Aderonke Salihu","is_ca":false},{"name":"Abimbola G. Akintola","is_ca":false},{"name":"Shuib Basri","is_ca":false},{"name":"Ramoni Tirimisiyu Amosa","is_ca":false},{"name":"Nasiru Kehinde Salahdeen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0455757640572681,"gpt":0.2618194326055124,"spread":0.2162436685482443,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00245335,0.001197976,0.001356433,0.001565243,0.000487122,0.0009775446,0.001474916,0.001214204,0.001603001],"category_scores_gemma":[0.004763815,0.0004562252,0.001471751,0.001626622,0.000338271,0.001188229,0.0005036662,0.001804373,0.0005316693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009702861,"about_ca_system_score_gemma":0.001005397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01910162,"about_ca_topic_score_gemma":0.02104216,"domain_scores_codex":[0.9991805,0.0003274181,0.00005541994,0.0001841449,0.0001240981,0.0001284314],"domain_scores_gemma":[0.996787,0.002348622,0.0002407888,0.00009967372,0.0004456591,0.00007835674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001104639,0.00009035058,0.004878108,0.00007577883,0.00006043909,0.0000679415,0.00003828889,0.9367439,0.0004185254,0.003154517,0.001732046,0.05262966],"study_design_scores_gemma":[0.000002620211,0.000007588523,0.0001944594,0.000004768626,0.000005693789,0.000005011017,0.000004026695,0.9982612,0.00004326522,0.001343025,0.0001258915,0.000002453592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1434499,0.003056345,0.8461737,0.001052766,0.0001736878,0.0001510604,0.001883486,0.001343171,0.002715916],"genre_scores_gemma":[0.8563179,0.001297094,0.1367107,0.0002686435,0.0001689175,0.0002336195,0.002682502,0.00006546447,0.002255093],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01910162,"threshold_uncertainty_score":0.03798085,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2052835589","doi":"10.1016/j.jretai.2013.04.001","title":"Capturing the Evolution of Customer–Firm Relationships: How Customers Become More (or Less) Valuable Over Time","year":2013,"lang":"en","type":"article","venue":"Journal of Retailing","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":30,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; University of Guelph","funders":"","keywords":"Customer base; Business; Marketing; Markov chain; Customer lifetime value; Market segmentation; Event (particle physics); Customer retention; Computer science; Service (business)","authors":[{"name":"Tanya Mark","is_ca":true},{"name":"Katherine N. Lemon","is_ca":false},{"name":"Mark Vandenbosch","is_ca":true},{"name":"Jan Bulla","is_ca":false},{"name":"Antonello Maruotti","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03364060857057146,"gpt":0.2424506853413488,"spread":0.2088100767707773,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001182868,0.0001846583,0.0002270189,0.001435171,0.0004038658,0.002824392,0.0005818459,0.001212446,0.002609397],"category_scores_gemma":[0.01158641,0.0001986053,0.0002179227,0.002397994,0.0004427177,0.003568774,0.0007606423,0.0008747852,0.0004894648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006317972,"about_ca_system_score_gemma":0.0005327366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01067274,"about_ca_topic_score_gemma":0.02004525,"domain_scores_codex":[0.9994454,0.0002096451,0.00003476449,0.000141067,0.00009606493,0.00007302815],"domain_scores_gemma":[0.9953902,0.002513826,0.0009569231,0.0003720475,0.0004143189,0.0003527463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002868314,0.0003204168,0.8885192,0.0001006801,0.0002072989,0.0001824131,0.003998586,0.008976498,0.003978824,0.005497911,0.001402406,0.08652898],"study_design_scores_gemma":[0.00001334942,0.000229479,0.8531495,0.00005648478,0.0001176337,0.000416524,0.006421342,0.1202237,0.001782322,0.01325785,0.004264903,0.00006680193],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953387,0.0001790742,0.002012038,0.0002400767,0.000006632322,0.000007327405,0.0002140392,0.00001592165,0.001986244],"genre_scores_gemma":[0.9983218,0.00005980206,0.001022161,0.00003392232,0.000004765102,0.00000461309,0.000186063,0.000005191634,0.0003616799],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01067274,"threshold_uncertainty_score":0.02122128,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2727112484","doi":"10.5430/air.v6n2p93","title":"Analysis of imbalanced data set problem: The case of churn prediction for telecommunication","year":2017,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Feature selection; Computer science; Data mining; Random forest; Feature (linguistics); Machine learning; Artificial intelligence","authors":[{"name":"Chun Gui","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4113565419835101,"gpt":0.4777785203359856,"spread":0.06642197835247554,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004880753,0.001008921,0.001308149,0.002712412,0.0008874303,0.001043764,0.001203118,0.001427225,0.0007188329],"category_scores_gemma":[0.01062622,0.0002541103,0.001071287,0.002165698,0.0006650546,0.001419252,0.0006052174,0.001292781,0.0001290385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001213827,"about_ca_system_score_gemma":0.0007514209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007082934,"about_ca_topic_score_gemma":0.004802805,"domain_scores_codex":[0.9982656,0.0006258702,0.000122801,0.0003668323,0.0004021049,0.0002168281],"domain_scores_gemma":[0.9918282,0.005754322,0.0009233888,0.0005198026,0.0007509647,0.0002233272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007956236,0.0007996667,0.09416442,0.0004855164,0.0003810976,0.00134563,0.0003612588,0.7832174,0.002299813,0.004594165,0.006783982,0.1047713],"study_design_scores_gemma":[0.0000115171,0.00006406829,0.01271539,0.00001612171,0.00002451151,0.0001237891,0.0001660815,0.9819812,0.0008962736,0.003480325,0.00050808,0.00001261294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.839963,0.001355828,0.151788,0.001855898,0.0002556935,0.0001823112,0.002354628,0.000498243,0.001746352],"genre_scores_gemma":[0.9656759,0.0002585066,0.03142334,0.0000961214,0.0001113012,0.0000932147,0.00182038,0.00002439837,0.0004968157],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007082934,"threshold_uncertainty_score":0.02581221,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099336464","doi":"10.1109/cnsr.2005.5","title":"A Churn-Strategy Alignment Model for Managers in Mobile Telecom","year":2005,"lang":"en","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Saint Mary's University","funders":"","keywords":"Computer science; Perspective (graphical); Mobile telephony; Telecommunications; Adaptation (eye); Customer relationship management; Business; Artificial intelligence; Mobile radio; Database","authors":[{"name":"Wei Yu","is_ca":true},{"name":"Dawn Jutla","is_ca":true},{"name":"Seshadri Sivakumar","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02624441487781401,"gpt":0.258766158915085,"spread":0.232521744037271,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002436811,0.0005740799,0.0006634099,0.001398969,0.0005513637,0.00205053,0.001085474,0.001289866,0.002435556],"category_scores_gemma":[0.005791204,0.0004357151,0.0004727934,0.001533239,0.0005232453,0.001720513,0.0008016702,0.001298046,0.00061473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002104394,"about_ca_system_score_gemma":0.001824545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01424911,"about_ca_topic_score_gemma":0.01628149,"domain_scores_codex":[0.9993289,0.0003207451,0.00003676353,0.0001151021,0.00006497672,0.0001335721],"domain_scores_gemma":[0.997177,0.001912205,0.0003361123,0.00007462429,0.0002744503,0.0002255809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007069246,0.001032985,0.2963327,0.0001519142,0.0002944549,0.0005031665,0.002207166,0.5430251,0.0009798441,0.03319399,0.005796447,0.1157752],"study_design_scores_gemma":[0.00001510731,0.00009076158,0.0114923,0.00001359706,0.00002145438,0.00003220432,0.0002241475,0.9810085,0.00006611811,0.006653883,0.0003706611,0.00001119575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9219822,0.0003491473,0.07046164,0.001803769,0.00002971043,0.0001158817,0.0005616347,0.0002220194,0.004473934],"genre_scores_gemma":[0.9905472,0.0001409252,0.007438089,0.00006750938,0.00001708127,0.000102817,0.0004231958,0.00001618344,0.001246815],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01424911,"threshold_uncertainty_score":0.02833235,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3213928715","doi":"10.3390/jrfm14110544","title":"Churn Management in Telecommunications: Hybrid Approach Using Cluster Analysis and Decision Trees","year":2021,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"CHAID; Decision tree; Market segmentation; Computer science; Cluster analysis; Data mining; Segmentation; Cluster (spacecraft); Artificial intelligence; Machine learning; Business; Marketing","authors":[{"name":"Mirjana Pejić Bach","is_ca":false},{"name":"Jasmina Pivar","is_ca":false},{"name":"Božidar Jaković","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01424882378387014,"gpt":0.2415394299382436,"spread":0.2272906061543735,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003200262,0.0008818481,0.001552194,0.004816175,0.0009747015,0.002573543,0.001670277,0.00149476,0.0008814247],"category_scores_gemma":[0.005769643,0.0005270344,0.001510106,0.0047615,0.0005566648,0.001895606,0.001072071,0.001285917,0.0002772363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001981614,"about_ca_system_score_gemma":0.002102743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01502491,"about_ca_topic_score_gemma":0.01535123,"domain_scores_codex":[0.9972572,0.001171979,0.0002089289,0.0004120853,0.0007174296,0.0002324748],"domain_scores_gemma":[0.994738,0.003435108,0.0005115701,0.0002302309,0.0009147343,0.0001702998],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001558068,0.0004355385,0.0202018,0.0003220911,0.0004272069,0.0001743702,0.0007206096,0.637673,0.001772295,0.0172097,0.002812776,0.3180948],"study_design_scores_gemma":[0.000005400586,0.00003069185,0.001452943,0.00002224601,0.00002293469,0.0000184763,0.00009415471,0.9900284,0.0003361616,0.007520269,0.0004533071,0.00001490355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04417238,0.0005662212,0.9516172,0.0006120195,0.00003517047,0.000241412,0.000268768,0.0006000672,0.001886685],"genre_scores_gemma":[0.5458022,0.0005715046,0.4511511,0.0001616031,0.0001144926,0.0003184349,0.0006356656,0.0000683505,0.001176767],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01502491,"threshold_uncertainty_score":0.02987492,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2338439532","doi":"","title":"Ecommerce \"Stickiness\" for Customer Retention","year":2000,"lang":"en","type":"article","venue":"The Journal of Internet Banking and Commerce","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":24,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; World Wide Web","authors":[{"name":"Martin A. W. Nemzow","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02541991866429508,"gpt":0.245800612386774,"spread":0.220380693722479,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009889515,0.0005476865,0.0004776742,0.001257935,0.00122412,0.002479167,0.0004886159,0.001685216,0.01563953],"category_scores_gemma":[0.009572243,0.000177922,0.0005369178,0.001455789,0.001215324,0.003188601,0.00138427,0.002146503,0.0009366406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009402403,"about_ca_system_score_gemma":0.0008728789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001896209,"about_ca_topic_score_gemma":0.003222017,"domain_scores_codex":[0.9994129,0.0001260519,0.00003752451,0.0001078543,0.0001804906,0.0001351962],"domain_scores_gemma":[0.9912978,0.00453413,0.001671096,0.0006719746,0.0008155075,0.001009488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002622771,0.001813342,0.3646286,0.0008422105,0.0006177554,0.001849425,0.002016739,0.01839179,0.01462835,0.2284623,0.01360438,0.3505223],"study_design_scores_gemma":[0.0002112628,0.00231115,0.6502587,0.0003140907,0.0004768336,0.00153862,0.002646447,0.03995686,0.004754774,0.286901,0.0104664,0.000163849],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8981839,0.001866729,0.01384004,0.00325991,0.0003900524,0.0001026543,0.0003265534,0.0001693038,0.08186093],"genre_scores_gemma":[0.9967439,0.0001019619,0.0007506834,0.0001836198,0.0001061707,0.000007766287,0.00003433412,0.000008819243,0.002062668],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01563953,"threshold_uncertainty_score":0.05231947,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4283018748","doi":"10.3390/jrfm15060269","title":"A Machine Learning Framework towards Bank Telemarketing Prediction","year":2022,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; Machine learning; Exploit; Classifier (UML); Artificial intelligence; Transparency (behavior); Coding (social sciences); Predictive modelling; Field (mathematics); Data mining; Computer security; Mathematics","authors":[{"name":"Stéphane Cédric Koumetio Tekouabou","is_ca":false},{"name":"Ştefan Cristian Gherghina","is_ca":false},{"name":"Hamza Toulni","is_ca":false},{"name":"Pedro Neves Mata","is_ca":false},{"name":"Mário Nuno Mata","is_ca":false},{"name":"José Moleiro Martins","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.006709919720596814,"gpt":0.2013547263224188,"spread":0.194644806601822,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002457259,0.0009042856,0.0009723122,0.002092371,0.0005414661,0.002020701,0.001627562,0.001613958,0.001794784],"category_scores_gemma":[0.005164178,0.0004315042,0.0009112356,0.001633679,0.000730393,0.001405164,0.001177955,0.002512618,0.0007388545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001132421,"about_ca_system_score_gemma":0.001316466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01060208,"about_ca_topic_score_gemma":0.00651602,"domain_scores_codex":[0.9988568,0.000509418,0.00006310533,0.0002733032,0.0002266528,0.00007084123],"domain_scores_gemma":[0.9978998,0.001413259,0.0001589871,0.0001000444,0.0003552809,0.00007266724],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006145517,0.0001262721,0.003105605,0.0001072091,0.0001059148,0.0001560226,0.00008157458,0.8572874,0.0006781562,0.02665624,0.00254155,0.1090926],"study_design_scores_gemma":[0.000002218731,0.00001260064,0.0002358829,0.00001350605,0.000004395515,0.00001054767,0.000009612964,0.9869394,0.0001291812,0.01184246,0.0007946883,0.000005515314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01233688,0.001769277,0.9819605,0.00106752,0.000102292,0.00005431725,0.0002510797,0.0005661089,0.001891977],"genre_scores_gemma":[0.6029821,0.00217794,0.3878227,0.0005362227,0.000602046,0.0004075743,0.00102156,0.0001060571,0.004343871],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01060208,"threshold_uncertainty_score":0.02108073,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3016177134","doi":"10.1007/s00521-020-04850-6","title":"Optimum profit-driven churn decision making: innovative artificial neural networks in telecom industry","year":2020,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":21,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial neural network; Profit (economics); Artificial intelligence; Machine learning; Data mining; Analytics; Set (abstract data type)","authors":[{"name":"Ruholla Jafari-Marandi","is_ca":false},{"name":"Joshua Denton","is_ca":false},{"name":"Adnan Idris","is_ca":false},{"name":"Brian Smith","is_ca":false},{"name":"Abbas Keramati","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03689159694372936,"gpt":0.2918008907290897,"spread":0.2549092937853603,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002950573,0.0005364134,0.001332975,0.0006051629,0.0004117739,0.001480761,0.0009906722,0.002059687,0.001093911],"category_scores_gemma":[0.007106522,0.0006451433,0.0004685326,0.0008535165,0.0007672018,0.001730664,0.0007551577,0.001399236,0.00009350858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001692543,"about_ca_system_score_gemma":0.001361318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01254393,"about_ca_topic_score_gemma":0.009351083,"domain_scores_codex":[0.9992587,0.000379323,0.00003727808,0.000119358,0.00009887901,0.0001065032],"domain_scores_gemma":[0.9953577,0.003837346,0.0002390062,0.00004816991,0.0004389981,0.00007882085],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007423879,0.00003620981,0.0004293095,0.00002376943,0.0000233977,0.00001781226,0.00002313873,0.9852551,0.0001591704,0.002447339,0.0001996435,0.01131088],"study_design_scores_gemma":[0.0000021527,0.000004305837,0.00003416114,0.000001653142,0.000001882563,7.623119e-7,0.00000200664,0.99911,0.00002674235,0.0008031109,0.0000120647,0.000001124477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2861831,0.002789168,0.7017812,0.002086522,0.0001505125,0.00007817824,0.0000989248,0.0002000695,0.006632361],"genre_scores_gemma":[0.9774318,0.0003600166,0.02034668,0.0001089622,0.00007035598,0.00003704298,0.00003294086,0.00001633059,0.001595889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01254393,"threshold_uncertainty_score":0.0249418,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140160830","doi":"10.5267/j.msl.2012.02.012","title":"CEO emotional bias and investment decision, Bayesian network method","year":2012,"lang":"en","type":"article","venue":"Management Science Letters","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Bayesian network; Bayesian probability; Investment (military); Psychology; Econometrics; Computer science; Investment decisions; Statistics; Artificial intelligence; Business; Economics; Mathematics; Finance; Behavioral economics; Political science","authors":[{"name":"Mohammad Ali Azouzi","is_ca":false},{"name":"Anis Jarboui","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02741503400903809,"gpt":0.266601307388149,"spread":0.2391862733791109,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002993745,0.0005001139,0.0004988411,0.001647342,0.0003615544,0.0008333371,0.000581697,0.0007129483,0.003055082],"category_scores_gemma":[0.01648875,0.0002666825,0.0003605885,0.001200561,0.0004029884,0.001309584,0.0004792623,0.0006601026,0.0002659647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008637119,"about_ca_system_score_gemma":0.0005385921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005024691,"about_ca_topic_score_gemma":0.003720199,"domain_scores_codex":[0.9984266,0.001081744,0.00005932192,0.0001843406,0.0001613546,0.0000866831],"domain_scores_gemma":[0.9935039,0.00537925,0.0005885183,0.0001459177,0.0002632986,0.0001191488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001739367,0.001246739,0.2289685,0.000374821,0.0005800055,0.0005273611,0.001330524,0.4039975,0.002872596,0.07950959,0.003416194,0.2754368],"study_design_scores_gemma":[0.00005169342,0.0001237738,0.02115578,0.00004651434,0.00007672349,0.0001103473,0.0001866755,0.9425252,0.0005076728,0.03410115,0.001072829,0.00004168989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5522376,0.0007119193,0.437925,0.0008591305,0.00007512413,0.0003240624,0.0006658121,0.000187404,0.007013996],"genre_scores_gemma":[0.939843,0.000406994,0.05717694,0.00007468453,0.00005421443,0.0002204802,0.0004671486,0.0000130672,0.001743405],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005024691,"threshold_uncertainty_score":0.01583266,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2975392813","doi":"10.1109/cig.2019.8848033","title":"Mining Player In-game Time Spending Regularity for Churn Prediction in Free Online Games","year":2019,"lang":"en","type":"article","venue":"2019 IEEE Conference on Games (CoG)","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science","authors":[{"name":"Wanshan Yang","is_ca":false},{"name":"Ting Huang","is_ca":false},{"name":"Junlin Zeng","is_ca":false},{"name":"Gemeng Yang","is_ca":false},{"name":"Jintian Cai","is_ca":true},{"name":"Lijun Chen","is_ca":false},{"name":"Shivakant Mishra","is_ca":false},{"name":"Youjian Liu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03699918568312889,"gpt":0.2615649434211816,"spread":0.2245657577380527,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006304321,0.0008033794,0.0007336861,0.003151589,0.0003171167,0.0008171868,0.0006467575,0.0005693777,0.001211928],"category_scores_gemma":[0.005016145,0.0002584457,0.000537605,0.00195926,0.0003110473,0.001117594,0.0006488777,0.0006380584,0.0005684171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006246203,"about_ca_system_score_gemma":0.0004610614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007184514,"about_ca_topic_score_gemma":0.0193534,"domain_scores_codex":[0.9994524,0.0001251331,0.00005354398,0.0001708506,0.00009830801,0.00009985195],"domain_scores_gemma":[0.9973843,0.001240685,0.0006149814,0.0002354758,0.0002180973,0.0003066357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001078194,0.001230208,0.7282068,0.0003758214,0.000360878,0.000494235,0.0007694366,0.08609458,0.00472639,0.003628144,0.00892852,0.1641069],"study_design_scores_gemma":[0.00002687634,0.0001849293,0.2259963,0.00005316331,0.00006424944,0.0003162755,0.000335812,0.7634441,0.001901842,0.00468341,0.002951181,0.00004188541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9352776,0.0004702971,0.05403737,0.0002464856,0.000039667,0.0001264466,0.006164216,0.0007754118,0.002862324],"genre_scores_gemma":[0.9808218,0.0001043371,0.01354302,0.00003881902,0.00001900443,0.00007662387,0.004564987,0.00003472898,0.0007965696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007184514,"threshold_uncertainty_score":0.01428539,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2555747031","doi":"10.5267/j.dsl.2016.8.006","title":"Customer satisfaction measurement using fuzzy neural network","year":2016,"lang":"en","type":"article","venue":"Decision Science Letters","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Customer satisfaction; Artificial neural network; Fuzzy logic; Computer science; Business; Artificial intelligence; Marketing","authors":[{"name":"Ayad Hendalianpour","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05814368012837891,"gpt":0.2783122470646177,"spread":0.2201685669362387,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00128399,0.0003754554,0.0004482383,0.001277108,0.0002747762,0.0008320807,0.0004049582,0.0005870446,0.0009234868],"category_scores_gemma":[0.002741113,0.000144873,0.0003592568,0.001624541,0.0002327172,0.0008585431,0.0004519112,0.0004018373,0.0001295406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000885718,"about_ca_system_score_gemma":0.0003370735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005175645,"about_ca_topic_score_gemma":0.003140087,"domain_scores_codex":[0.9988486,0.0004793992,0.00007783291,0.0001470301,0.0003658723,0.00008127181],"domain_scores_gemma":[0.99913,0.0003392471,0.0001277645,0.00004254274,0.0003333626,0.00002705881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001309934,0.0006381728,0.04264532,0.0003071445,0.0002888089,0.0001587915,0.0003821079,0.3068956,0.0177034,0.005641771,0.002180969,0.6218479],"study_design_scores_gemma":[0.00000827778,0.00009973522,0.00506686,0.000009247045,0.00001445584,0.00001444906,0.0000409544,0.9919654,0.001959759,0.0006176655,0.0001886981,0.00001450686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4535304,0.0005206288,0.5374815,0.000300309,0.00006002899,0.0001816607,0.0002020624,0.0006098887,0.007113458],"genre_scores_gemma":[0.9708565,0.0001001367,0.02836668,0.00002663632,0.00001094651,0.00005814118,0.00008779944,0.000005647236,0.0004873606],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005175645,"threshold_uncertainty_score":0.01029104,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2563000706","doi":"10.5430/air.v6n1p80","title":"Can machine learning techniques predict customer dissatisfaction? A feasibility study for the automotive industry","year":2016,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Automotive industry; Competitor analysis; Computer science; Customer satisfaction; Service (business); Support vector machine; Artificial intelligence; Machine learning; Marketing; Business; Engineering","authors":[{"name":"Stefan Meinzer","is_ca":false},{"name":"Ulf Jensen","is_ca":false},{"name":"Alexander Thamm","is_ca":false},{"name":"Joachim Hornegger","is_ca":false},{"name":"Bjoern M. Eskofier","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2094813873278795,"gpt":0.4236811888324536,"spread":0.2141998015045742,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002575838,0.0006167611,0.0005257599,0.0009596362,0.000294228,0.0006962111,0.0006639608,0.001150599,0.001615762],"category_scores_gemma":[0.004902544,0.0001942487,0.0006361897,0.0007777902,0.0002117735,0.0009100686,0.0002854265,0.0005868233,0.0003923354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005318535,"about_ca_system_score_gemma":0.0005983559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006324039,"about_ca_topic_score_gemma":0.003350215,"domain_scores_codex":[0.9989098,0.0006164345,0.00005243792,0.0001202993,0.0001925366,0.0001085398],"domain_scores_gemma":[0.9958519,0.002901985,0.0001237972,0.0001398562,0.0008385165,0.0001440115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00411977,0.01046623,0.3878596,0.0004563814,0.0003524943,0.0008991894,0.0004720109,0.1527764,0.02146593,0.001218563,0.003515438,0.4163979],"study_design_scores_gemma":[0.0000762201,0.003010419,0.05317919,0.00002825385,0.00006653236,0.00008212258,0.0005831338,0.9391879,0.002843302,0.0003525779,0.0005649076,0.00002542113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9820212,0.0004223404,0.01536014,0.0006027886,0.00003662646,0.0001457343,0.0001419761,0.0001027829,0.001166376],"genre_scores_gemma":[0.990422,0.0001809703,0.00862091,0.00004185064,0.00002205073,0.00005732515,0.0001820725,0.000003643244,0.000469051],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006324039,"threshold_uncertainty_score":0.01362252,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2001890608","doi":"10.1016/j.eswa.2012.10.028","title":"An enhanced Customer Relationship Management classification framework with Partial Focus Feature Reduction","year":2012,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":16,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Computer science; Data mining; Customer relationship management; Dimensionality reduction; Preprocessor; Feature (linguistics); Curse of dimensionality; Data pre-processing; Focus (optics); Set (abstract data type); Artificial intelligence; Data set; Data classification; Pattern recognition (psychology); Database","authors":[{"name":"Yan Tu","is_ca":true},{"name":"Zijiang Yang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02467471025088682,"gpt":0.274360643891005,"spread":0.2496859336401182,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009697602,0.0005876491,0.00104813,0.001693112,0.0005787765,0.001048832,0.00172493,0.0009307128,0.002361544],"category_scores_gemma":[0.00110424,0.0002855667,0.0009287021,0.001271295,0.000192919,0.001035,0.0009452781,0.0009265507,0.001150809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004984864,"about_ca_system_score_gemma":0.001149491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01273484,"about_ca_topic_score_gemma":0.01626362,"domain_scores_codex":[0.9993902,0.0001006184,0.0000286047,0.0001318616,0.0002612828,0.00008735451],"domain_scores_gemma":[0.9994895,0.0001137916,0.00003028303,0.00005959152,0.0002742138,0.000032594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003205833,0.0006845481,0.003350261,0.0001083661,0.0001458484,0.0001163737,0.00008980397,0.03882309,0.01974949,0.00493681,0.010333,0.9213418],"study_design_scores_gemma":[0.00001689512,0.00007719326,0.001779768,0.000009861456,0.0000515073,0.00006563176,0.00002717523,0.9881969,0.004408801,0.002585846,0.002762928,0.00001745685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03026549,0.0004533802,0.9628605,0.0002439487,0.00004462386,0.0001487454,0.0005854098,0.003450394,0.001947514],"genre_scores_gemma":[0.3536271,0.000256407,0.6372741,0.0003099448,0.0001252004,0.0002930924,0.002325395,0.0001673574,0.005621326],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01273484,"threshold_uncertainty_score":0.02532142,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162619115","doi":"10.5267/j.msl.2015.2.004","title":"Market basket analysis in insurance industry","year":2015,"lang":"en","type":"article","venue":"Management Science Letters","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Business; Insurance industry; Market analysis; Actuarial science; Marketing","authors":[{"name":"Marzieh Vahidi Roodpishi","is_ca":false},{"name":"Reza Aghajan Nashtaei","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0221726137536907,"gpt":0.2432677884839359,"spread":0.2210951747302452,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001606964,0.0004814014,0.0007520599,0.01066471,0.0007784702,0.001930228,0.0003502379,0.0003643774,0.003622739],"category_scores_gemma":[0.002717861,0.0003040438,0.001063131,0.008372488,0.0003276543,0.001104938,0.0005369024,0.000340592,0.0007801054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009540907,"about_ca_system_score_gemma":0.00102761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01866809,"about_ca_topic_score_gemma":0.01567491,"domain_scores_codex":[0.9988571,0.0003449603,0.0001050246,0.0001615247,0.0003841178,0.0001471948],"domain_scores_gemma":[0.9986541,0.0004918567,0.0002584,0.00008494676,0.0004030125,0.0001075531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001736751,0.001079273,0.5190488,0.0007704837,0.001077263,0.001798153,0.001463869,0.0203286,0.006751535,0.01806722,0.01426236,0.4136159],"study_design_scores_gemma":[0.00008647552,0.0005806431,0.6803544,0.000186189,0.0002829183,0.0009470846,0.003343603,0.2881853,0.002680603,0.009489456,0.01373228,0.00013099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9517098,0.002068922,0.03018234,0.0007256812,0.0001126239,0.0005004226,0.003873756,0.0004465662,0.0103799],"genre_scores_gemma":[0.961682,0.0009064089,0.03044603,0.00006157945,0.00006790557,0.0001629604,0.003543856,0.00003990501,0.003089341],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01866809,"threshold_uncertainty_score":0.03711885,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169759309","doi":"10.5430/jms.v5n1p33","title":"Research Intelligent Precision Marketing of E-commerce Based on the Big Data","year":2014,"lang":"en","type":"article","venue":"Journal of Management and Strategy","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Big data; Computer science; Database transaction; Cluster analysis; Transaction data; Division (mathematics); Path (computing); Marketing research; Data science; E-commerce; Marketing; Data mining; Business; Artificial intelligence; Database; World Wide Web; Mathematics","authors":[{"name":"Jianhui Zhang","is_ca":false},{"name":"Junxuan Zhu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1738625832570846,"gpt":0.335038754616296,"spread":0.1611761713592114,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001965302,0.0004755297,0.0005859349,0.002274371,0.0008327843,0.005258495,0.0007908319,0.0008750928,0.001444121],"category_scores_gemma":[0.004944656,0.0003174882,0.0006312913,0.002573454,0.001484016,0.008630451,0.001041596,0.001297474,0.0002575684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00203359,"about_ca_system_score_gemma":0.001603289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003639926,"about_ca_topic_score_gemma":0.003298556,"domain_scores_codex":[0.9983655,0.0004518295,0.00007594858,0.0002938299,0.0006872391,0.0001257774],"domain_scores_gemma":[0.9975075,0.001332743,0.0003362349,0.0002578086,0.0004760479,0.00008967079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001266862,0.0002021516,0.04594591,0.0006483661,0.0003464722,0.0004086784,0.001647467,0.07917631,0.003310357,0.5758821,0.007836365,0.2844692],"study_design_scores_gemma":[0.00002392483,0.0001043359,0.02197725,0.0001964567,0.0001370177,0.0003165292,0.001667363,0.630819,0.003408211,0.3061653,0.03510017,0.00008443301],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2168722,0.0141432,0.6923478,0.01142361,0.0004629155,0.0003425511,0.0005486516,0.0006508071,0.06320828],"genre_scores_gemma":[0.9407105,0.00418458,0.05042781,0.0005445371,0.0003115765,0.00009340005,0.0002845748,0.00004510303,0.003398006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005258495,"threshold_uncertainty_score":0.01475483,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2887528003","doi":"10.1155/2018/3635107","title":"Application of Customer Segmentation for Electronic Toll Collection: A Case Study","year":2018,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Natural Science Basic Research Program of Shaanxi Province; Fundamental Research Funds for the Central Universities; Ministry of Education of the People's Republic of China","keywords":"Cluster analysis; Computer science; Segmentation; Market segmentation; Data mining; Sample (material); Customer relationship management; Payment; Decision tree; Big data; Scale (ratio); Artificial intelligence; Marketing; Business; Database","authors":[{"name":"Chao Qian","is_ca":false},{"name":"Meng Yang","is_ca":false},{"name":"Peiqi Li","is_ca":false},{"name":"Shuguang Li","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01158567676713836,"gpt":0.2777961086099889,"spread":0.2662104318428506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001393107,0.0004573392,0.0003205964,0.001673706,0.001792972,0.001314827,0.001327072,0.001921509,0.002617487],"category_scores_gemma":[0.003127812,0.0002622268,0.0007755284,0.003089878,0.0006943078,0.001099107,0.0009730676,0.0007868718,0.0003662863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001847021,"about_ca_system_score_gemma":0.001125622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0101538,"about_ca_topic_score_gemma":0.01451403,"domain_scores_codex":[0.9982292,0.0007872275,0.0000967109,0.0001627369,0.0004513645,0.0002727826],"domain_scores_gemma":[0.9969532,0.001707148,0.0002973773,0.0003377684,0.0004225709,0.0002818921],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001600248,0.006484243,0.3913303,0.001172845,0.0004102839,0.05058005,0.01676115,0.1578999,0.01532141,0.02547762,0.01634917,0.3166128],"study_design_scores_gemma":[0.0002468953,0.002119912,0.2349685,0.0002304341,0.0003506397,0.01842329,0.06875464,0.5862422,0.03513031,0.009001007,0.04417581,0.0003563918],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9745086,0.0001437998,0.01747632,0.0004871785,0.00003011255,0.000268401,0.000447326,0.0001045658,0.006533748],"genre_scores_gemma":[0.9858138,0.0001504874,0.0120403,0.00007021119,0.00002091882,0.00007213769,0.0002123337,0.0000162427,0.001603519],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0101538,"threshold_uncertainty_score":0.0201894,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2295690276","doi":"10.1109/icmla.2015.120","title":"Predicting Churn of Expert Respondents in Social Networks Using Data Mining Techniques: A Case Study of Stack Overflow","year":2015,"lang":"en","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Random forest; Logistic regression; Asset (computer security); Incentive; Data mining; Machine learning; Precision and recall; Support vector machine; Recall; Artificial neural network; Data science; Artificial intelligence; Social network (sociolinguistics); World Wide Web; Computer security; Social media","authors":[{"name":"Ifeoma Adaji","is_ca":true},{"name":"Julita Vassileva","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1864493925840011,"gpt":0.3684325344312371,"spread":0.181983141847236,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025538,0.0003425837,0.0002787035,0.001884931,0.0007496043,0.0006335368,0.0005143221,0.0009359426,0.0006140916],"category_scores_gemma":[0.009045051,0.0001793456,0.0002811221,0.001203178,0.0003512174,0.001111828,0.0004808735,0.0005452179,0.0001994692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006281946,"about_ca_system_score_gemma":0.00042907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01135688,"about_ca_topic_score_gemma":0.01910321,"domain_scores_codex":[0.9991405,0.0003969213,0.00007815486,0.0001274719,0.0001335023,0.0001234421],"domain_scores_gemma":[0.9885474,0.007872064,0.001659431,0.0003205662,0.0009552666,0.0006452586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002169579,0.0006182656,0.9594425,0.00005366577,0.0000586765,0.001266076,0.005420632,0.006063209,0.00191269,0.0003181013,0.0006543415,0.02397493],"study_design_scores_gemma":[0.00003510634,0.0008003431,0.680575,0.00009286976,0.00008348079,0.001324696,0.02172693,0.2867313,0.004762472,0.00131398,0.002467407,0.00008631773],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9990385,0.00001587908,0.0006452826,0.0000675474,0.000001323429,0.0000132313,0.00006169412,0.00000869059,0.0001479379],"genre_scores_gemma":[0.9978303,0.00002858046,0.001734808,0.00002786732,0.000004242997,0.00001339197,0.000131055,0.000002850475,0.0002267946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01135688,"threshold_uncertainty_score":0.02258158,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4323048015","doi":"10.18280/mmep.100135","title":"The Implementation of RFM Analysis to Customer Profiling Using K-Means Clustering","year":2023,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Universitas Pelita Harapan","keywords":"Profiling (computer programming); Cluster analysis; Computer science; Business; Artificial intelligence; Programming language","authors":[{"name":"Okky Putra Barus","is_ca":false},{"name":"Celine Nathasya","is_ca":false},{"name":"Jefri Junifer Pangaribuan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03726340031003235,"gpt":0.2650079497523581,"spread":0.2277445494423257,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002497107,0.001068446,0.0009922954,0.004178135,0.001867867,0.001883963,0.001682088,0.001169497,0.004726034],"category_scores_gemma":[0.0095123,0.00057069,0.001678933,0.004005301,0.0005160738,0.001131394,0.001251802,0.001495186,0.003627697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001159167,"about_ca_system_score_gemma":0.001997088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02230787,"about_ca_topic_score_gemma":0.01941797,"domain_scores_codex":[0.9971619,0.0007685524,0.0002787519,0.0006028469,0.0009259723,0.0002620523],"domain_scores_gemma":[0.9966127,0.0008058443,0.0002257467,0.000547696,0.001743087,0.00006487506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002311243,0.000468245,0.01121285,0.0003456235,0.0002918619,0.0002477092,0.001967819,0.111084,0.0162192,0.01456204,0.01236701,0.8310025],"study_design_scores_gemma":[0.00002580411,0.0001171705,0.01081889,0.00005970743,0.00005106355,0.0002200819,0.0008937634,0.9446589,0.01909233,0.008731772,0.01518402,0.0001464719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02192861,0.00004995154,0.9693368,0.0001457371,0.00009781026,0.0003444307,0.0003839366,0.004847234,0.00286538],"genre_scores_gemma":[0.1122487,0.00004375113,0.8847503,0.0000459648,0.00002443399,0.0003198081,0.0005140754,0.0003045683,0.0017484],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02230787,"threshold_uncertainty_score":0.04435605,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3021984135","doi":"10.1007/978-3-030-47358-7_33","title":"Customer Segmentation and Churn Prediction in Online Retail","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Customer lifetime value; Computer science; Market segmentation; Analytic hierarchy process; Order (exchange); Customer base; Cluster analysis; Churning; Variable (mathematics); Loyalty business model; Customer retention; Process (computing); Customer relationship management; Logistic regression; Marketing; Data mining; Operations research; Business; Artificial intelligence; Machine learning; Mathematics; Database","authors":[{"name":"Nilay Jha","is_ca":true},{"name":"Dhruv Parekh","is_ca":true},{"name":"Malek Mouhoub","is_ca":true},{"name":"Varun Makkar","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02319109800859011,"gpt":0.2336048805914675,"spread":0.2104137825828774,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000979838,0.0005982162,0.0009102334,0.001321996,0.000422428,0.001103638,0.0008270584,0.0009352811,0.002409862],"category_scores_gemma":[0.002808735,0.0005227727,0.0005139533,0.001732369,0.0003399941,0.001593646,0.0004801308,0.001035537,0.0008225008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009584119,"about_ca_system_score_gemma":0.0005199632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01391116,"about_ca_topic_score_gemma":0.01648819,"domain_scores_codex":[0.999676,0.00009445183,0.00001583513,0.00007826411,0.00006395302,0.00007142092],"domain_scores_gemma":[0.9976725,0.001862831,0.0001314526,0.00005497933,0.0001433226,0.0001348955],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.001263948,0.0007130069,0.196751,0.0001389372,0.00024378,0.000378717,0.0003255365,0.4590427,0.001484624,0.007287716,0.01649901,0.3158711],"study_design_scores_gemma":[0.000004315424,0.00004245767,0.01393195,0.00001245636,0.00001491112,0.00003966559,0.00004257457,0.982381,0.0002105869,0.002983381,0.0003289335,0.000007801282],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9259451,0.005189248,0.05753719,0.0009126337,0.0001485909,0.00003238506,0.0009684326,0.0006258046,0.008640683],"genre_scores_gemma":[0.9877216,0.0007375969,0.005888897,0.00005476718,0.0001421162,0.00001814622,0.0008342775,0.00005253709,0.004550025],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01391116,"threshold_uncertainty_score":0.02766037,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2514100103","doi":"10.1016/j.engappai.2016.01.028","title":"Flight deck crew reserve: From data to forecasting","year":2016,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":9,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"Mitacs","keywords":"Computer science; Crew; Schedule; Operations research; Aeronautics","authors":[{"name":"Amir-Hosein Homaie-Shandizi","is_ca":true},{"name":"Vahid Partovi Nia","is_ca":true},{"name":"Michel Gamache","is_ca":true},{"name":"Bruno Agard","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1232846478045199,"gpt":0.2948713271558751,"spread":0.1715866793513551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001572331,0.0007468577,0.0006201885,0.002596722,0.0002704162,0.001934442,0.0009209044,0.00153636,0.00169809],"category_scores_gemma":[0.008065355,0.0003474567,0.0003379581,0.00339105,0.0003969476,0.002234356,0.000638444,0.001351523,0.001310401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009177829,"about_ca_system_score_gemma":0.0006287627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03332311,"about_ca_topic_score_gemma":0.02176166,"domain_scores_codex":[0.9994449,0.0001714862,0.00004569193,0.0001522861,0.0001295548,0.0000560404],"domain_scores_gemma":[0.9952857,0.002824613,0.0003766766,0.0006828905,0.0006343763,0.0001957667],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008013415,0.0005237217,0.3515553,0.0002785799,0.0003109001,0.0003849856,0.0003113578,0.2311138,0.001769437,0.004989592,0.0491284,0.3588327],"study_design_scores_gemma":[0.0000248567,0.00007045893,0.06158499,0.00009552605,0.00007270004,0.00006494275,0.0002587943,0.9183481,0.001599277,0.009248509,0.00859302,0.00003894921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8459238,0.006653042,0.06773628,0.008136022,0.0007587321,0.0001312044,0.05155229,0.004372967,0.01473577],"genre_scores_gemma":[0.9642267,0.0009250326,0.0142355,0.0001700889,0.0002544865,0.00004735489,0.01844245,0.00007322078,0.001625228],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03332311,"threshold_uncertainty_score":0.06625831,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3129637043","doi":"10.1109/icmla51294.2020.00118","title":"Predicting purchase probability of retail items using an ensemble learning approach and historical data","year":2020,"lang":"en","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Voting; Computer science; Boosting (machine learning); Supply chain; Ensemble learning; Random forest; Gradient boosting; Machine learning; Artificial intelligence; Convolution (computer science); Artificial neural network","authors":[{"name":"Archika Sharma","is_ca":true},{"name":"M. Omair Shafiq","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2145058848057406,"gpt":0.2697378562035638,"spread":0.05523197139782324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001333916,0.0006759043,0.0009848844,0.001914275,0.0003326687,0.000812497,0.0007222986,0.0007609389,0.0007317223],"category_scores_gemma":[0.002226376,0.0003088753,0.0007610085,0.001685531,0.0001430408,0.001442104,0.0003890171,0.0007849804,0.0003548999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004460387,"about_ca_system_score_gemma":0.000487281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01055087,"about_ca_topic_score_gemma":0.0161543,"domain_scores_codex":[0.9994614,0.0001142908,0.00004607781,0.0001602615,0.0001378909,0.00008015974],"domain_scores_gemma":[0.9983975,0.0008043955,0.0001588286,0.0001980956,0.0003838067,0.00005734188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000210635,0.0003893759,0.06853368,0.00004646742,0.0002417433,0.0001889039,0.00007724082,0.6716179,0.003122678,0.0009947473,0.00160605,0.2529707],"study_design_scores_gemma":[0.000001051149,0.00002044944,0.002709347,0.000002596306,0.00001213951,0.0000145774,0.000009819131,0.9964622,0.0003825354,0.0002890803,0.0000920837,0.000004120868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6199999,0.0006110535,0.3747317,0.0002951415,0.00008008639,0.00006316532,0.0007918337,0.0008796414,0.002547367],"genre_scores_gemma":[0.9539024,0.0002131681,0.04383533,0.00003626562,0.00004050293,0.00002427286,0.0008525514,0.00001729152,0.001078206],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01055087,"threshold_uncertainty_score":0.02097893,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2054847839","doi":"10.4236/ib.2013.51a006","title":"Forecasting and the Role of Churn in Software-as-a-Service Business Models","year":2013,"lang":"en","type":"article","venue":"iBusiness","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Software as a service; Revenue; Business model; Service (business); Computer science; Key (lock); Software; Revenue model; Process management; Business; Marketing; Software development; Finance; Computer security","authors":[{"name":"Anthony E. R. Sukow","is_ca":false},{"name":"Rebecca Grant","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0184646020107836,"gpt":0.1953226592340002,"spread":0.1768580572232167,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003779688,0.0007834806,0.0008266613,0.001471337,0.0009407547,0.002308699,0.001179785,0.001285915,0.001125079],"category_scores_gemma":[0.01584025,0.0005356493,0.000513609,0.001458157,0.001083018,0.002744232,0.0009515166,0.001643026,0.00018812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002413076,"about_ca_system_score_gemma":0.001258429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02773011,"about_ca_topic_score_gemma":0.01870739,"domain_scores_codex":[0.9988793,0.0005595917,0.0000430684,0.000149483,0.0002015781,0.0001669553],"domain_scores_gemma":[0.9907219,0.007303536,0.0008547652,0.0002254112,0.0006040811,0.0002903283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004395252,0.00004147609,0.01082625,0.00002586421,0.00003154059,0.0001100145,0.0002840771,0.9374724,0.000221224,0.03739811,0.0007505126,0.01279462],"study_design_scores_gemma":[0.000001136158,0.000008778658,0.0005701646,0.000008103738,0.000003038331,0.00001538272,0.00003440092,0.9895348,0.00003700443,0.009562906,0.0002182403,0.000005995552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5680585,0.002053477,0.4063454,0.004397941,0.0001255168,0.0000834063,0.0002687622,0.0004454312,0.01822148],"genre_scores_gemma":[0.9892492,0.0004835588,0.008649206,0.00006260579,0.00005378181,0.00002232352,0.00008216099,0.00002807441,0.001369005],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02773011,"threshold_uncertainty_score":0.0551374,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2058871015","doi":"10.1057/dbm.2009.8","title":"Potential moderators of the link between rate plan suitability and customer tenure: A case in the Canadian mobile telecommunications industry","year":2009,"lang":"en","type":"article","venue":"Journal of Database Marketing & Customer Strategy Management","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":8,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Business; Customer retention; Customer equity; Marketing; Linkage (software); Telecommunications; Customer profitability; Customer intelligence; Computer science","authors":[{"name":"Ken Kwong-Kay Wong","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02417529280843517,"gpt":0.2631146009368366,"spread":0.2389393081284014,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00660947,0.0003514587,0.0007533025,0.001843309,0.01030827,0.00443318,0.003039979,0.002784131,0.01166154],"category_scores_gemma":[0.04511422,0.0004393064,0.0006498426,0.002840263,0.005227061,0.001567028,0.003050701,0.003324797,0.0004837584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01562532,"about_ca_system_score_gemma":0.03121038,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.8452424,"about_ca_topic_score_gemma":0.9098861,"domain_scores_codex":[0.992139,0.003115408,0.0002315939,0.0006733399,0.001214028,0.002626521],"domain_scores_gemma":[0.9307645,0.04613131,0.008567496,0.00193146,0.005876705,0.006728646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003924813,0.0006190164,0.966618,0.00004169446,0.0001125899,0.000751278,0.0182926,0.0004134191,0.0004820269,0.004088234,0.001653087,0.006535591],"study_design_scores_gemma":[0.00007087661,0.000248888,0.9210203,0.00009339098,0.0002618575,0.0002071924,0.07007925,0.002613498,0.0003263476,0.001615417,0.003389792,0.00007323221],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928668,0.0001402264,0.0001996108,0.001671773,0.00001280713,0.00003718189,0.0001028034,0.000006083448,0.004962782],"genre_scores_gemma":[0.9986213,0.00004039996,0.0000998965,0.0001047207,0.000007163605,0.00001489374,0.00003119239,0.000003656725,0.001076771],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1547576,"threshold_uncertainty_score":0.311338,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406931539","doi":"10.1201/9781003559139-9","title":"Enhancing customer segmentation: RFM analysis and K-Means clustering implementation","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Cluster analysis; Computer science; Segmentation; Market segmentation; Business; Data mining; Artificial intelligence; Marketing","authors":[{"name":"G. Ramkumar","is_ca":false},{"name":"J. Bhuvaneswari","is_ca":true},{"name":"V. Sujatha","is_ca":false},{"name":"Suresh Kumar","is_ca":false},{"name":"Chandra Kala Ramasamy","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01442596950370599,"gpt":0.2593668106935632,"spread":0.2449408411898572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018966,0.0006863736,0.0005526361,0.001674819,0.0008373277,0.00170519,0.001261654,0.0009227053,0.004556269],"category_scores_gemma":[0.004563317,0.0003193506,0.0007406987,0.002443946,0.0005488176,0.001538096,0.001122026,0.0008206441,0.001898155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001581458,"about_ca_system_score_gemma":0.001411275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01229136,"about_ca_topic_score_gemma":0.01433354,"domain_scores_codex":[0.9985995,0.0005704955,0.00005436855,0.0002162657,0.0004263342,0.0001330538],"domain_scores_gemma":[0.9985801,0.0006735486,0.0001192127,0.000131869,0.0004569733,0.00003836842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002487898,0.0003399,0.007618574,0.0001979904,0.00007483921,0.0001222988,0.001477392,0.07163658,0.007692338,0.03138455,0.01411202,0.8650947],"study_design_scores_gemma":[0.00002869079,0.0001884716,0.01003761,0.00008329522,0.00004673236,0.0001639399,0.001406664,0.9405521,0.01099808,0.01866886,0.01773898,0.00008666596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08117817,0.0003815474,0.8829267,0.001037817,0.0001212829,0.0003353088,0.0003135535,0.00396415,0.02974143],"genre_scores_gemma":[0.2637179,0.0002118207,0.7278159,0.0001840043,0.00003549561,0.0002132989,0.000380382,0.0003954819,0.00704558],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01229136,"threshold_uncertainty_score":0.02443963,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391842518","doi":"10.1017/asb.2024.6","title":"Integration of traditional and telematics data for efficient insurance claims prediction","year":2024,"lang":"en","type":"article","venue":"Astin Bulletin","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Telematics; Computer science; Business; Data science; Computer security; Actuarial science; Internet privacy; Telecommunications","authors":[{"name":"Hashan Peiris","is_ca":true},{"name":"Himchan Jeong","is_ca":true},{"name":"Jae‐Kwang Kim","is_ca":false},{"name":"Hangsuck Lee","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05605451650429507,"gpt":0.2535846521676571,"spread":0.197530135663362,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003335399,0.0005035976,0.0007091164,0.002742356,0.0003305064,0.001507169,0.00109898,0.0009603016,0.001496375],"category_scores_gemma":[0.007653269,0.0003977459,0.0006422765,0.003630161,0.0003384684,0.001918943,0.001629628,0.001298461,0.0004196641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006080515,"about_ca_system_score_gemma":0.0008020446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007360207,"about_ca_topic_score_gemma":0.007105684,"domain_scores_codex":[0.9984681,0.0005768951,0.0001152619,0.0003363559,0.0003730972,0.000130251],"domain_scores_gemma":[0.9960049,0.001755252,0.0006579445,0.0007018691,0.0007103555,0.00016969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006370614,0.001024835,0.2660119,0.0001282006,0.0004988631,0.0004855418,0.0003758946,0.2890234,0.006092062,0.006519347,0.005399294,0.4238036],"study_design_scores_gemma":[0.0000121245,0.0000528662,0.02334124,0.00001990866,0.00003436115,0.00004278231,0.00009591108,0.9703371,0.001596776,0.002951815,0.001499734,0.000015334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5854551,0.0009604557,0.40608,0.001111773,0.0001112918,0.0001168611,0.001846922,0.001396485,0.002921095],"genre_scores_gemma":[0.9483047,0.0001229022,0.04911703,0.00006602584,0.00007856714,0.00003688138,0.001705121,0.00003134814,0.0005374181],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007360207,"threshold_uncertainty_score":0.01763952,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2766985263","doi":"10.1109/icitech.2017.8079966","title":"Integrating SOM and fuzzy k-means clustering for customer classification in personalized recommendation system for non-text based transactional data","year":2017,"lang":"en","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Cluster analysis; Recommender system; Data mining; Novelty; Transaction data; Process (computing); Customer relationship management; Fuzzy logic; Fuzzy clustering; E-commerce; Domain (mathematical analysis); Artificial intelligence; Machine learning; World Wide Web; Database; Database transaction","authors":[{"name":"Sukhpreet Kaur Dhaliwal","is_ca":true},{"name":"Ngoc Nhu Van","is_ca":true},{"name":"Manmeet Dhaliwal","is_ca":true},{"name":"Jon Rokne","is_ca":true},{"name":"Reda Alhajj","is_ca":true},{"name":"Tansel Özyer","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09803492859455532,"gpt":0.3182888625252332,"spread":0.2202539339306779,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000747506,0.0007248641,0.0009891043,0.002620226,0.0007794705,0.0011589,0.0009550956,0.001136113,0.001706118],"category_scores_gemma":[0.001559154,0.000414801,0.001329607,0.002664266,0.0002564784,0.001038021,0.0003751125,0.0006012672,0.001210993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000850616,"about_ca_system_score_gemma":0.000835878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02722879,"about_ca_topic_score_gemma":0.03675558,"domain_scores_codex":[0.9994042,0.00006697215,0.00006074052,0.0001552801,0.0002110911,0.0001016821],"domain_scores_gemma":[0.9993212,0.0001271838,0.00003380603,0.0000669496,0.0004170168,0.0000337806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007666078,0.0006407121,0.01410445,0.0002981779,0.0004858628,0.0002590776,0.0002928904,0.08209252,0.02150278,0.001101614,0.008888694,0.8695667],"study_design_scores_gemma":[0.00002692476,0.0001175888,0.006805046,0.00002950115,0.0001060525,0.000156651,0.0001894347,0.9737977,0.01500534,0.001171235,0.002533837,0.00006073725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1884273,0.001037518,0.7948381,0.0003957899,0.0002969618,0.0004203371,0.001345407,0.006775036,0.006463595],"genre_scores_gemma":[0.5702801,0.0005861116,0.4221806,0.0001446837,0.00008630118,0.0002084371,0.001339565,0.0001182427,0.005056004],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02722879,"threshold_uncertainty_score":0.05414063,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410081179","doi":"10.1016/j.dss.2025.114470","title":"Product return prediction in live streaming e-commerce with cross-modal contrastive transformer","year":2025,"lang":"en","type":"article","venue":"Decision Support Systems","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"Beijing Municipal Commission of Education; National Natural Science Foundation of China","keywords":"Modal; Transformer; Computer science; Product (mathematics); Mathematics; Engineering; Voltage; Electrical engineering; Chemistry; Geometry","authors":[{"name":"Wen Zhang","is_ca":false},{"name":"Rui Xie","is_ca":false},{"name":"Pei Quan","is_ca":false},{"name":"Zhenzhong Ma","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01389323321094472,"gpt":0.2673340555854815,"spread":0.2534408223745367,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006303309,0.0003668976,0.0005049177,0.0009383533,0.0001816956,0.0005553233,0.0004780805,0.0004530175,0.001186209],"category_scores_gemma":[0.001204208,0.0001529934,0.0003662246,0.0007773497,0.0002226351,0.0009859087,0.0004204698,0.0004421776,0.0003768491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003606848,"about_ca_system_score_gemma":0.0002486237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008036703,"about_ca_topic_score_gemma":0.005806129,"domain_scores_codex":[0.9998218,0.00003276262,0.000009906242,0.00004713747,0.00004565262,0.0000427535],"domain_scores_gemma":[0.9994702,0.0003060499,0.00003267815,0.00003484488,0.000120544,0.00003573971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005152359,0.001578925,0.0741914,0.0001530744,0.0001667692,0.00119182,0.0002237507,0.2590421,0.03846025,0.004169807,0.004011376,0.6116584],"study_design_scores_gemma":[0.000004220131,0.00003462935,0.002780418,0.000001407832,0.000007179095,0.00003574435,0.00001810608,0.9953989,0.001352423,0.000296614,0.00006655404,0.000003749251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8911089,0.0003656585,0.1055226,0.0001064847,0.0000484866,0.00002469404,0.000285373,0.0006292331,0.001908719],"genre_scores_gemma":[0.9929442,0.00006459423,0.006224969,0.0000135447,0.00001108387,0.000004661895,0.0001913579,0.00001189568,0.0005335783],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008036703,"threshold_uncertainty_score":0.01597983,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2011055298","doi":"10.5539/ass.v10n13p169","title":"Churn Analytics on Indian Prepaid Mobile Services","year":2014,"lang":"en","type":"article","venue":"Asian Social Science","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Business; Analytics; Conceptual model; Mobile telephony; Marketing; Computer science; Telecommunications; Data science","authors":[{"name":"P. Rajeswari","is_ca":false},{"name":"P. Ravilochanan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009773615803502642,"gpt":0.2516488590767018,"spread":0.2418752432731992,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005599588,0.0004233923,0.0003438726,0.003188651,0.0006438906,0.001126355,0.0006250526,0.0003950655,0.00175997],"category_scores_gemma":[0.002445108,0.0001248562,0.0004557154,0.00340636,0.0002888878,0.0007948254,0.0007434665,0.000850477,0.0007512616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001177942,"about_ca_system_score_gemma":0.0005586828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05108016,"about_ca_topic_score_gemma":0.04387864,"domain_scores_codex":[0.9995469,0.00008159331,0.00003829205,0.00007176295,0.0001589007,0.0001025104],"domain_scores_gemma":[0.9981616,0.0007729121,0.0002618888,0.00014735,0.0005120268,0.0001442155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001343259,0.001234967,0.515465,0.0005043433,0.0002378181,0.002388745,0.004818868,0.1420384,0.005726358,0.006456216,0.03547053,0.2843156],"study_design_scores_gemma":[0.00001242429,0.0002131554,0.2421931,0.00006573138,0.00005145105,0.0003980668,0.002534156,0.7418943,0.002989607,0.002049883,0.007547648,0.00005049137],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9858636,0.0004540039,0.003045631,0.0005329087,0.00003414605,0.00004500747,0.003400391,0.0008161287,0.005808105],"genre_scores_gemma":[0.9911419,0.000254174,0.002357775,0.00005291234,0.00001967405,0.00002662808,0.00411409,0.00004468401,0.001987994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05108016,"threshold_uncertainty_score":0.1015657,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3206052219","doi":"10.3390/jrfm14100481","title":"A Novel Model Structured on Predictive Churn Methods in a Banking Organization","year":2021,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Random forest; Computer science; Decision tree; Customer base; Logistic regression; Context (archaeology); Predictive modelling; Artificial neural network; Econometrics; Business; Marketing; Data mining; Artificial intelligence; Machine learning; Economics","authors":[{"name":"Leonardo José Silveira","is_ca":false},{"name":"Plácido Rogério Pinheiro","is_ca":false},{"name":"Leopoldo Melo","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0126362890742379,"gpt":0.2535957041644796,"spread":0.2409594150902417,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001481572,0.0006625822,0.000779483,0.001125751,0.0005558049,0.001750231,0.001714886,0.001499179,0.002723691],"category_scores_gemma":[0.00322531,0.0003335261,0.0008274848,0.001317754,0.0005682823,0.001616608,0.0009066011,0.001293443,0.0005114292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009288472,"about_ca_system_score_gemma":0.001509222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01392733,"about_ca_topic_score_gemma":0.01011061,"domain_scores_codex":[0.9993395,0.0002225974,0.00003422568,0.0001958633,0.0001202666,0.00008746954],"domain_scores_gemma":[0.9988288,0.0007996701,0.0001012707,0.00004550713,0.0001852361,0.00003944554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001609239,0.00019348,0.00767197,0.0001694634,0.0001156163,0.0002858668,0.0003294091,0.8501076,0.001199473,0.03603449,0.002924648,0.1008069],"study_design_scores_gemma":[0.000003801619,0.00001898502,0.0002799922,0.00001111652,0.000009730781,0.00002061366,0.00001121481,0.9958204,0.00007971402,0.003218555,0.0005206831,0.000005171356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0599135,0.0009485784,0.9288582,0.001130129,0.0001484971,0.0001363541,0.0003793919,0.0006132462,0.007872139],"genre_scores_gemma":[0.8161306,0.001149266,0.1718708,0.0002808188,0.0002604563,0.0003971167,0.0006274341,0.00008427796,0.009199067],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01392733,"threshold_uncertainty_score":0.02769256,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3002583521","doi":"10.1109/besc48373.2019.8963436","title":"A Case Study of Predicting Banking Customers Behaviour by Using Data Mining","year":2019,"lang":"en","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Data mining; Customer relationship management; Artificial neural network; Data warehouse; Variety (cybernetics); Association rule learning; Data modeling; Data science; Machine learning; Artificial intelligence; Database","authors":[{"name":"Xujuan Zhou","is_ca":false},{"name":"Ghazal Bargshady","is_ca":false},{"name":"Moloud Abdar","is_ca":true},{"name":"Xiaohui Tao","is_ca":false},{"name":"Raj Gururajan","is_ca":false},{"name":"Ka Ching Chan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06840287939409515,"gpt":0.2967648518924933,"spread":0.2283619724983982,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001975327,0.0006160954,0.0005653468,0.001500106,0.001159961,0.001312164,0.001313223,0.002053031,0.002110684],"category_scores_gemma":[0.006321154,0.000316363,0.0006071991,0.002833068,0.0005119755,0.001244872,0.0006370124,0.0009228279,0.0005379735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001106686,"about_ca_system_score_gemma":0.0009358659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01883399,"about_ca_topic_score_gemma":0.02055861,"domain_scores_codex":[0.9986456,0.0006120777,0.0001132246,0.0001713053,0.000324882,0.0001328728],"domain_scores_gemma":[0.9947296,0.003818366,0.0002306223,0.0003323715,0.0006442052,0.0002447241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001924696,0.004447132,0.3411618,0.001203847,0.0004615153,0.02870978,0.004942457,0.3354864,0.008431057,0.008323214,0.02094095,0.2439672],"study_design_scores_gemma":[0.0001467911,0.0009852087,0.0703373,0.0001199104,0.000141968,0.003271558,0.004349076,0.893927,0.009331203,0.003662421,0.01363451,0.00009291044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9665326,0.0004855224,0.0226694,0.00208737,0.00006648273,0.0003398157,0.00163041,0.0003811323,0.005807275],"genre_scores_gemma":[0.9669125,0.0002791366,0.02969143,0.0001248503,0.00002649688,0.0001016762,0.0008482501,0.00002598501,0.001989654],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01883399,"threshold_uncertainty_score":0.03744876,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2751548166","doi":"10.5539/mas.v11n9p151","title":"Unsupervised Learning Framework for Customer Requisition and Behavioral Pattern Classification","year":2017,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Tertiary Education Trust Fund","keywords":"Computer science; Purchasing; Unsupervised learning; Database transaction; Behavioral pattern; Market segmentation; Partition (number theory); Data mining; Artificial intelligence; Knowledge management; Business; Marketing; Database; Mathematics","authors":[{"name":"Udoinyang G. Inyang","is_ca":false},{"name":"Okure O. Obot","is_ca":false},{"name":"Moses E. Ekpenyong","is_ca":false},{"name":"Aliu M. Bolanle","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07425045765811449,"gpt":0.3257252671083438,"spread":0.2514748094502293,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00149093,0.0006516811,0.0009816563,0.002089775,0.0005310076,0.001053224,0.00165671,0.001039457,0.001526801],"category_scores_gemma":[0.002755108,0.0003734955,0.001344947,0.001876589,0.0006139863,0.0008780215,0.0008593489,0.001035832,0.0006619289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001062023,"about_ca_system_score_gemma":0.001643693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0110979,"about_ca_topic_score_gemma":0.01106237,"domain_scores_codex":[0.9988598,0.0003695576,0.00008441311,0.0002946116,0.000266663,0.0001250275],"domain_scores_gemma":[0.9989214,0.0004960173,0.0001214187,0.00008961499,0.0003270464,0.00004449398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001745465,0.0003620606,0.007765681,0.0002378928,0.0003323316,0.0002309282,0.0003017655,0.488759,0.004770142,0.02692336,0.004651178,0.4654911],"study_design_scores_gemma":[0.000003378995,0.00002248159,0.0006088056,0.000006897081,0.000009367487,0.00002170883,0.0000208565,0.992811,0.0003288511,0.005585291,0.0005737359,0.000007621714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009281896,0.000226194,0.9886599,0.0001467434,0.00002434233,0.00007147378,0.0001866938,0.0005934946,0.0008094003],"genre_scores_gemma":[0.4305507,0.0004680991,0.5612261,0.0001848911,0.0001460591,0.0006951968,0.001541747,0.0001330339,0.005054106],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0110979,"threshold_uncertainty_score":0.02206659,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4286518196","doi":"10.18280/ria.360304","title":"Churn Prediction Model Improvement Using Automated Machine Learning with Social Network Parameters","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Centrality; Computer science; Social network (sociolinguistics); Revenue; Competition (biology); Data science; Machine learning; Artificial intelligence; Social network analysis; Revenue model; Social media; World Wide Web; Business","authors":[{"name":"Marin Mandić","is_ca":false},{"name":"Goran Kraljević","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04086890788483465,"gpt":0.2510407057785353,"spread":0.2101717978937007,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002449306,0.001126282,0.001111187,0.002326748,0.0006017662,0.001111928,0.001077208,0.001032462,0.001356189],"category_scores_gemma":[0.006001775,0.0004234754,0.001069212,0.001187097,0.0003531621,0.001354823,0.0006627631,0.001165011,0.0005193207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001360411,"about_ca_system_score_gemma":0.001193925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02189766,"about_ca_topic_score_gemma":0.01635047,"domain_scores_codex":[0.9989229,0.0004843457,0.00007670468,0.0002359041,0.0001596335,0.0001204276],"domain_scores_gemma":[0.9954329,0.003135947,0.0003604814,0.0002539668,0.0007253487,0.00009133471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009973338,0.0002358224,0.01147404,0.00003667727,0.00009473695,0.00006619718,0.00006325911,0.9195463,0.0005989484,0.0007207101,0.001090973,0.06597264],"study_design_scores_gemma":[0.000001521539,0.000008407219,0.0002945945,0.000001591239,0.000002937862,0.000002978491,0.000002109767,0.9993715,0.00007047796,0.0001977499,0.00004446965,0.00000170565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4939311,0.0007843902,0.4943468,0.0009691645,0.0001574258,0.0002471835,0.0008320133,0.003821061,0.004910843],"genre_scores_gemma":[0.951079,0.0001162957,0.04616873,0.0001060651,0.00006395254,0.0001438456,0.0006050838,0.00006332216,0.001653768],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02189766,"threshold_uncertainty_score":0.04354042,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963699115","doi":"10.1109/icdmw.2018.00122","title":"Generating Realistic Sequences of Customer-Level Transactions for Retail Datasets","year":2018,"lang":"en","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; McGill University","funders":"","keywords":"Computer science; Recurrent neural network; Task (project management); Database transaction; Transaction data; Purchasing; Artificial intelligence; Machine learning; Data mining; Artificial neural network; Database; Marketing","authors":[{"name":"Thang Doan","is_ca":true},{"name":"Neil Veira","is_ca":true},{"name":"Brian Keng","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0884931706702073,"gpt":0.2961337664315699,"spread":0.2076405957613626,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001727585,0.001017988,0.0005862712,0.001289126,0.0003839707,0.000879812,0.002078721,0.002134729,0.003002744],"category_scores_gemma":[0.007047857,0.0005485589,0.001226178,0.00148081,0.0006950453,0.001268739,0.001057654,0.002400612,0.002018565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001079651,"about_ca_system_score_gemma":0.0005452436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004096343,"about_ca_topic_score_gemma":0.01075223,"domain_scores_codex":[0.9987586,0.000500397,0.0000811792,0.0003611593,0.0002033848,0.00009532309],"domain_scores_gemma":[0.9971707,0.001531589,0.0002172254,0.000624944,0.0003337997,0.0001218101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001099109,0.001819447,0.07247401,0.0006796606,0.0004419438,0.0009666948,0.000276755,0.7521771,0.003879116,0.00768066,0.0665494,0.09195615],"study_design_scores_gemma":[0.00008260756,0.0002053906,0.01073416,0.00003249107,0.00002493321,0.000237484,0.0001050457,0.9745432,0.001684557,0.005572553,0.006737615,0.00004011916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7145602,0.002233456,0.1581473,0.002653745,0.0005843934,0.0007865891,0.1082863,0.006735673,0.006012349],"genre_scores_gemma":[0.6896356,0.000586387,0.09327912,0.0006261212,0.0001296389,0.0005861991,0.2114211,0.0002133589,0.003522492],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004096343,"threshold_uncertainty_score":0.01004517,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2538056999","doi":"10.1109/gcis.2013.22","title":"Conducting Efficient and Cost-Effective Targeted Marketing Using Data Mining Techniques","year":2013,"lang":"en","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Business; Process (computing); Customer relationship management; Marketing; Big data; Marketing management; Computer science; Data mining","authors":[{"name":"Ling Liu","is_ca":true},{"name":"Zijiang Yang","is_ca":true},{"name":"Younes Benslimane","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08817398783075041,"gpt":0.296343134058398,"spread":0.2081691462276476,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002679287,0.001278024,0.001787402,0.004691307,0.0008279115,0.002671379,0.001269211,0.001119041,0.001365533],"category_scores_gemma":[0.007568468,0.0007223967,0.001415677,0.003335187,0.0002646582,0.002112645,0.0008706843,0.0009575339,0.001186189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005152161,"about_ca_system_score_gemma":0.001739105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003119268,"about_ca_topic_score_gemma":0.004017852,"domain_scores_codex":[0.9977551,0.0007004156,0.0003014985,0.0003390744,0.0007572852,0.0001465774],"domain_scores_gemma":[0.9932659,0.004513634,0.0005886995,0.0004944339,0.001027629,0.0001097356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000311725,0.001317739,0.01659657,0.0007355856,0.0003661843,0.0004465841,0.0004967318,0.07420761,0.02528616,0.0031514,0.006509542,0.8705741],"study_design_scores_gemma":[0.0000800767,0.0003265663,0.009131269,0.0001497497,0.0001772452,0.0003721922,0.0008745484,0.9396918,0.02856585,0.01102338,0.009527076,0.00008036596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07428494,0.0008546173,0.9136534,0.0007884033,0.00005601975,0.001084191,0.001316159,0.00413569,0.00382657],"genre_scores_gemma":[0.193209,0.0006246683,0.8025006,0.0001210528,0.00004985833,0.0004979784,0.00189942,0.0001074168,0.0009900372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004691307,"threshold_uncertainty_score":0.01416957,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403097110","doi":"10.5206/cjils-rcsib.v47i2.17432","title":"The importance of the Ansoff matrix for the study of the information services market","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Information and Library Science","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Matrix (chemical analysis); Business; Computer science; Materials science; Composite material","authors":[{"name":"A. Ferreira","is_ca":false},{"name":"Maria Beatriz Marques","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.005467065366171056,"gpt":0.2012090633412155,"spread":0.1957419979750444,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003977634,0.0005246231,0.0005578237,0.008915111,0.00353659,0.007635259,0.0006451049,0.001280939,0.007823861],"category_scores_gemma":[0.0164298,0.0002343607,0.0004808843,0.01048226,0.005750437,0.01165135,0.003337543,0.001630682,0.001087651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004453097,"about_ca_system_score_gemma":0.005504258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01152559,"about_ca_topic_score_gemma":0.01212896,"domain_scores_codex":[0.996336,0.001849002,0.0002337085,0.0002312833,0.001118314,0.000231663],"domain_scores_gemma":[0.9865094,0.009393183,0.001202374,0.0003305966,0.001759087,0.0008053523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002084243,0.00002055344,0.003341244,0.0001292997,0.000006684029,0.0002678293,0.00356074,0.000528574,0.0002303205,0.9509672,0.006792257,0.03413453],"study_design_scores_gemma":[0.00001018577,0.0000626369,0.01067524,0.0005058611,0.00001293857,0.0006653279,0.01600407,0.007835622,0.0003893736,0.6872945,0.2764635,0.00008081218],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1250713,0.01602276,0.1533985,0.04434177,0.002291259,0.0007138909,0.001373443,0.0001923111,0.6565947],"genre_scores_gemma":[0.8739939,0.0111142,0.08380564,0.002003202,0.00126664,0.0007327078,0.0005959526,0.0001479667,0.02633976],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01152559,"threshold_uncertainty_score":0.03230959,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2039786694","doi":"10.1109/soli.2006.329026","title":"A Purchasing Sequences Data Mining Method for Customer Segmentation","year":2006,"lang":"en","type":"article","venue":"2006 IEEE International Conference on Service Operations and Logistics, and Informatics","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Saint Mary's University","funders":"","keywords":"Purchasing; Market segmentation; Computer science; Segmentation; Data mining; Customer base; Product (mathematics); Artificial intelligence; Machine learning; Business; Marketing; Mathematics","authors":[{"name":"Hai Wang","is_ca":true},{"name":"Shouhong Wang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1235778624919795,"gpt":0.3485582641360812,"spread":0.2249804016441018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00257768,0.001038735,0.001315501,0.006953406,0.0007984962,0.001212309,0.001250631,0.0009201036,0.002627772],"category_scores_gemma":[0.01020788,0.0005200754,0.00128798,0.00730105,0.0004278278,0.001987727,0.0007705821,0.001695115,0.001717704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006695265,"about_ca_system_score_gemma":0.001720207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003093403,"about_ca_topic_score_gemma":0.003635617,"domain_scores_codex":[0.9969736,0.0006944531,0.0004319712,0.0006601735,0.001143622,0.00009602569],"domain_scores_gemma":[0.994816,0.002674272,0.0005823879,0.0005171282,0.00126464,0.0001454726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004211158,0.0008138478,0.02123637,0.000616221,0.0003231939,0.0002451805,0.0006715094,0.02452014,0.009004927,0.007971648,0.01013368,0.9240422],"study_design_scores_gemma":[0.0001676505,0.0007227495,0.0181378,0.0002169904,0.0002265885,0.00155037,0.0005978277,0.88935,0.02879049,0.02120035,0.03881871,0.0002204168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02860639,0.0002973781,0.9607587,0.0002860461,0.00008866399,0.000895747,0.00366191,0.003226586,0.002178572],"genre_scores_gemma":[0.09188218,0.00019388,0.9016896,0.00009654527,0.00005455677,0.00112351,0.003742442,0.00008532401,0.001131917],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006953406,"threshold_uncertainty_score":0.01363224,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413096857","doi":"10.1109/ccict65753.2025.00084","title":"AI-Driven Sentiment Assessment and Automated Departmental Categorization for Customer Feedback","year":2025,"lang":"en","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Trinity College","funders":"","keywords":"Categorization; Computer science; Sentiment analysis; Text categorization; Artificial intelligence; Natural language processing","authors":[{"name":"Manik Rakhra","is_ca":false},{"name":"Tiyas Sarkar","is_ca":false},{"name":"Rajeev Kanday","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01205493627084921,"gpt":0.2984402822298059,"spread":0.2863853459589567,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001086939,0.0005628577,0.0002985246,0.0009833046,0.0003369082,0.0008566934,0.0007871159,0.0002934347,0.004157912],"category_scores_gemma":[0.004330766,0.0002214428,0.0004357953,0.0007173851,0.0002555982,0.0009218718,0.000503102,0.0007336347,0.002178085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001125789,"about_ca_system_score_gemma":0.001245513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006974154,"about_ca_topic_score_gemma":0.008852403,"domain_scores_codex":[0.9993648,0.0001775136,0.00004491688,0.0001420749,0.000210919,0.00005990457],"domain_scores_gemma":[0.9982467,0.000576435,0.0001666131,0.0001512257,0.0007782389,0.0000808585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008188612,0.0006526946,0.02108401,0.0003112777,0.0001264859,0.0002552563,0.0007643475,0.05688367,0.07752831,0.006356313,0.02584928,0.8093695],"study_design_scores_gemma":[0.00001873717,0.00008042608,0.006452053,0.00001347209,0.00001591001,0.00005392403,0.0000803383,0.9679558,0.01706922,0.002837816,0.005398223,0.00002402076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2072778,0.0001323776,0.7251246,0.0008438519,0.0002857724,0.0007798276,0.001767951,0.04599667,0.01779115],"genre_scores_gemma":[0.715121,0.00007231531,0.272496,0.0002852846,0.00006879612,0.0004010004,0.001880752,0.0004927362,0.00918205],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006974154,"threshold_uncertainty_score":0.01390958,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2988021717","doi":"10.69554/zgkn2372","title":"Using weak supervision to scale the development of machine-learning models for social media-based marketing research","year":2019,"lang":"en","type":"article","venue":"Applied marketing analytics","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Social media; Scale (ratio); Social media marketing; Computer science; Data science; Marketing; Knowledge management; Business; Psychology; Sociology; World Wide Web; Geography","authors":[{"name":"Jennifer Cutler","is_ca":true},{"name":"Aron Culotta","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.105073704937543,"gpt":0.3162203877653565,"spread":0.2111466828278135,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01790645,0.002157446,0.001635581,0.002080659,0.001219337,0.002346729,0.003611266,0.002429832,0.002960703],"category_scores_gemma":[0.05661105,0.001897488,0.00147184,0.001545878,0.002469277,0.007401041,0.004620202,0.007048253,0.002224747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002203169,"about_ca_system_score_gemma":0.002142402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00889663,"about_ca_topic_score_gemma":0.01075905,"domain_scores_codex":[0.9928651,0.004794384,0.000303563,0.001035662,0.0007938053,0.0002073832],"domain_scores_gemma":[0.9578995,0.03041849,0.001571373,0.005574967,0.003946838,0.0005888462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004376053,0.0006324333,0.01331429,0.0004848327,0.0004387524,0.0001600555,0.0007105467,0.6891044,0.004287459,0.02710345,0.009135493,0.2541906],"study_design_scores_gemma":[0.00001158282,0.00003820823,0.0003021449,0.00002616025,0.00001257083,0.000009112307,0.00002041976,0.9825117,0.0007924426,0.01532107,0.0009463551,0.000008267357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02925798,0.0006212736,0.9640539,0.001632398,0.000100528,0.0002590835,0.0002194765,0.001953118,0.001902228],"genre_scores_gemma":[0.4745678,0.0006722432,0.5178216,0.0007422052,0.0003580711,0.0007278154,0.001404478,0.0005177007,0.003188171],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01790645,"threshold_uncertainty_score":0.09469944,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411965264","doi":"10.1016/j.dajour.2025.100601","title":"A data-driven approach to customer lifetime value prediction using probability and machine learning models","year":2025,"lang":"en","type":"article","venue":"Decision Analytics Journal","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Langara College","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine learning; Value (mathematics); Artificial intelligence; Customer value; Economics","authors":[{"name":"Albert Wong","is_ca":true},{"name":"A.I. Ballesteros García","is_ca":true},{"name":"Yew-Wei Lim","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1077419021977437,"gpt":0.3044053623112366,"spread":0.1966634601134929,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00431178,0.0009721381,0.001263299,0.00268621,0.0005485414,0.00259628,0.002581358,0.00175931,0.002460204],"category_scores_gemma":[0.01868954,0.0008800862,0.001517228,0.002809751,0.0006216451,0.002809198,0.00108029,0.003093673,0.0006906636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001827792,"about_ca_system_score_gemma":0.001484805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0126976,"about_ca_topic_score_gemma":0.01032797,"domain_scores_codex":[0.9980655,0.0008186094,0.0001479806,0.000423553,0.0003916187,0.0001525841],"domain_scores_gemma":[0.9827312,0.01369589,0.001093324,0.0006829739,0.001514058,0.0002825205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001171747,0.0002623404,0.01457947,0.0001309714,0.0001456192,0.0002143843,0.0001317258,0.8828533,0.0004676175,0.02056405,0.002906633,0.07762683],"study_design_scores_gemma":[0.000002792978,0.00001243415,0.0004862132,0.000009037744,0.000005649702,0.00001633773,0.00001145227,0.992775,0.0001045583,0.006282868,0.0002858241,0.000007845735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05531165,0.0006519042,0.9371836,0.00216353,0.0001166906,0.0001868357,0.001215468,0.0007404414,0.002429978],"genre_scores_gemma":[0.7474892,0.0007170879,0.2453685,0.0004095195,0.0002879252,0.0003888083,0.00224164,0.0001043139,0.002992999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0126976,"threshold_uncertainty_score":0.0252474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3133751382","doi":"10.1109/access.2021.3064929","title":"Cancel-for-Any-Reason Insurance Recommendation Using Customer Transaction-Based Clustering","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Cluster analysis; Data mining; Revenue; Market segmentation; Database transaction; DBSCAN; Generalized entropy index; Index (typography); Artificial neural network; Artificial intelligence; Business; Database; Fuzzy clustering; Marketing; Finance","authors":[{"name":"Zhaleh Sadreddini","is_ca":true},{"name":"İlknur Dönmez","is_ca":false},{"name":"Halim Yanıkömeroğlu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07444771464393604,"gpt":0.3239853776228311,"spread":0.249537662978895,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000867972,0.0007976718,0.001279952,0.004134422,0.000708656,0.001412119,0.00145279,0.001216659,0.00144974],"category_scores_gemma":[0.002716097,0.0003734786,0.000954699,0.003832684,0.000233455,0.001327058,0.0005501387,0.000593591,0.0009617699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001260974,"about_ca_system_score_gemma":0.0008389269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03018534,"about_ca_topic_score_gemma":0.03868163,"domain_scores_codex":[0.9988202,0.0002140341,0.0001029243,0.0003563147,0.0003777997,0.0001287491],"domain_scores_gemma":[0.9986284,0.0004150114,0.0001433171,0.0001505373,0.0005437274,0.0001190662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008033451,0.00102499,0.03473395,0.0002178561,0.0006438551,0.0002639218,0.0003371072,0.3062307,0.003766645,0.002813338,0.02145866,0.6277056],"study_design_scores_gemma":[0.00001106877,0.00004419237,0.003836552,0.0000117696,0.00003589222,0.00004547846,0.00007414605,0.9931553,0.0007156584,0.001073815,0.0009707452,0.00002536189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3984725,0.001963515,0.5784501,0.001206114,0.0002373543,0.0008224989,0.002297738,0.003916761,0.01263333],"genre_scores_gemma":[0.8528864,0.0004121837,0.1398993,0.0001617093,0.0001037349,0.0001594824,0.002541106,0.00007400774,0.003762205],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03018534,"threshold_uncertainty_score":0.06001931,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403577487","doi":"10.1145/3627673.3679712","title":"OptDist: Learning Optimal Distribution for Customer Lifetime Value Prediction","year":2024,"lang":"en","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Value (mathematics); Computer science; Customer value; Distribution (mathematics); Machine learning; Mathematics; Economics","authors":[{"name":"Yunpeng Weng","is_ca":false},{"name":"Xing Tang","is_ca":false},{"name":"Fuyuan Lyu","is_ca":true},{"name":"Dugang Liu","is_ca":false},{"name":"Zexu Sun","is_ca":false},{"name":"Xiuqiang He","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0118806842799383,"gpt":0.2414078766402588,"spread":0.2295271923603205,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001814822,0.001510306,0.00147677,0.001782426,0.000595964,0.001001683,0.002638988,0.001501116,0.002036156],"category_scores_gemma":[0.005577814,0.0006225327,0.0009045106,0.0017489,0.0007256212,0.002614514,0.001410122,0.002308659,0.001066466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001578413,"about_ca_system_score_gemma":0.001710313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01118623,"about_ca_topic_score_gemma":0.01228615,"domain_scores_codex":[0.9989919,0.0002561405,0.00005195835,0.0003798999,0.0001913485,0.0001287862],"domain_scores_gemma":[0.9980714,0.001087898,0.0001537337,0.0002125855,0.0003520005,0.0001225502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000731864,0.0004586987,0.02911001,0.0001809494,0.0001404343,0.0002113481,0.0001495503,0.6371345,0.002488101,0.006041675,0.0292126,0.2941402],"study_design_scores_gemma":[0.00001422709,0.00001749429,0.0004723514,0.000004368975,0.000003942116,0.00002199839,0.0000109456,0.995796,0.0004374735,0.00261417,0.0006011878,0.000005804181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1311189,0.00199964,0.8496521,0.001501518,0.0001742915,0.0002205059,0.004525597,0.008724596,0.0020829],"genre_scores_gemma":[0.7695597,0.0007422677,0.2105522,0.0008268205,0.0002088485,0.0003557203,0.01268789,0.0004565588,0.004610005],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01118623,"threshold_uncertainty_score":0.02224225,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}