{"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"},"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001309543,0.0001562527,0.0002321958,0.0004625015,0.0001111926,0.0002425473,0.0002060626,0.00004160384,0.0009701252],"category_scores_gemma":[0.0006459671,0.0001306527,0.0001728292,0.0002571325,0.00002699438,0.001723642,0.00008534864,0.0003534836,0.0001892674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001669649,"about_ca_system_score_gemma":0.00003137289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003702631,"about_ca_topic_score_gemma":0.00002003195,"domain_scores_codex":[0.9986493,0.00005808856,0.0005569846,0.0001310262,0.0003859645,0.0002186544],"domain_scores_gemma":[0.9982894,0.0002612314,0.000953435,0.00008832412,0.0003824185,0.00002517435],"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":[0.005425933,0.0009010389,0.09187035,0.0004661689,0.0009430458,0.0002184149,0.002477387,0.001758515,0.02884487,0.001200752,0.1716799,0.6942137],"study_design_scores_gemma":[0.004624183,0.00008913168,0.1068427,0.002084726,0.0005137793,0.0002939992,0.00800389,0.02524159,0.002494776,0.0006165529,0.8482726,0.0009220646],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8598576,0.0002442125,0.0003163947,0.01293592,0.001459968,0.0001759952,0.000002392847,0.00005075253,0.1249567],"genre_scores_gemma":[0.9922853,0.00003795886,0.0006997605,0.001755299,0.004445164,0.000001938928,0.000002848112,0.00002516893,0.0007466279],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6932916,"threshold_uncertainty_score":0.9999431,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0002481743,0.00004902737,0.00009232998,0.0004159096,0.00009402357,0.00004586213,0.01322043,0.00001355105,0.00005665667],"category_scores_gemma":[0.0003422991,0.00003847254,0.00005899932,0.002084937,0.00005938235,0.0003560199,0.01262399,0.00007783778,0.00002044347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001513793,"about_ca_system_score_gemma":0.000006573547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001060465,"about_ca_topic_score_gemma":0.009237102,"domain_scores_codex":[0.9995095,0.00001909532,0.0002042117,0.00009848565,0.0001014956,0.00006721536],"domain_scores_gemma":[0.9822943,0.00003951334,0.0001511986,0.01747436,0.00003882292,0.000001795284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008056659,0.0005704682,0.7812495,0.00002657179,0.00009586105,8.35343e-8,0.0000596252,0.0005929776,0.0005871157,0.0212969,0.1547243,0.04078847],"study_design_scores_gemma":[0.0003337142,6.484771e-7,0.8316537,0.00002115397,0.0003836286,8.087569e-8,0.0001011118,0.03582037,0.00001611744,0.01452216,0.1170457,0.0001016426],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7911056,0.005462656,0.0001113724,0.1100296,0.0004170212,0.0003665581,0.00009473917,0.0001254677,0.09228699],"genre_scores_gemma":[0.9977733,0.00005513509,0.001259421,0.00008810051,0.00005202114,0.00000555725,0.0006602944,0.000004170518,0.0001020192],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2066677,"threshold_uncertainty_score":0.9953617,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000117183,0.0001046582,0.00008493835,0.00008317855,0.0001364912,0.0002062315,0.00006146786,0.00004867414,0.002578796],"category_scores_gemma":[0.000004880448,0.00009757567,0.0000303014,0.0001480008,0.00005438535,0.0007285221,0.000007416406,0.0001068997,0.001494912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007745518,"about_ca_system_score_gemma":0.000006921357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002005099,"about_ca_topic_score_gemma":0.00007801306,"domain_scores_codex":[0.999381,0.000006302252,0.0001088631,0.0001653455,0.0001228106,0.0002156875],"domain_scores_gemma":[0.9998562,0.000009366609,0.00002872536,0.00007213667,0.00002056424,0.00001302911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004820977,0.0003129444,0.05245376,0.00117792,0.0001694576,0.000119126,0.003540345,0.000565965,0.005193083,0.1140969,0.01740623,0.8044822],"study_design_scores_gemma":[0.00721271,0.0001063766,0.4841761,0.0003253157,0.0004028983,0.00007455734,0.06543994,0.003503664,0.001352239,0.01763719,0.4166959,0.003073114],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7554874,0.0003100793,0.000005589294,0.0005417027,0.00007838076,0.00007685205,4.671142e-7,0.00008510387,0.2434145],"genre_scores_gemma":[0.9919498,0.00001175088,0.00000837964,0.001233762,0.0005854702,0.000004672183,0.00001272024,0.00001175444,0.006181707],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8014091,"threshold_uncertainty_score":0.9992825,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003853245,0.0001340523,0.0001865018,0.000125411,0.00005922041,0.000401049,0.0001651695,0.00005838245,0.00003204076],"category_scores_gemma":[0.00007112691,0.000118623,0.00005051425,0.000227313,0.00002793193,0.0003581685,0.00006742297,0.00006683893,0.001809054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004091004,"about_ca_system_score_gemma":0.00001877924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009156422,"about_ca_topic_score_gemma":0.0001770747,"domain_scores_codex":[0.9989872,0.00001168921,0.0002699233,0.000183587,0.0003278719,0.0002197343],"domain_scores_gemma":[0.9994068,0.00002307069,0.0001521821,0.0002084219,0.0001804506,0.00002907669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000380113,0.0002973164,0.3504856,0.0006954384,0.000154515,0.00008395314,0.001432347,0.006662507,0.0007531989,0.1108682,0.5176761,0.0105107],"study_design_scores_gemma":[0.007148643,0.00002579842,0.01930409,0.0001387196,0.0001346051,0.00001646281,0.001985108,0.0601461,0.00005465187,0.002875595,0.9075302,0.0006400216],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7395355,0.001422443,0.005233957,0.0004670073,0.005765867,0.00100011,0.00000328632,0.0003922145,0.2461796],"genre_scores_gemma":[0.9943489,0.000003815728,0.0000270178,0.0002987931,0.00181887,0.00002982876,0.0000421929,0.00002699992,0.003403594],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3898541,"threshold_uncertainty_score":0.9989681,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001277185,0.0000971163,0.0001777806,0.001392362,0.00003898474,0.0001579584,0.0004326928,0.00006253878,0.0004163881],"category_scores_gemma":[0.000422301,0.00009182991,0.00003171328,0.001479266,0.0001111178,0.0009141505,0.0002674584,0.0002095281,0.0003320649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001593052,"about_ca_system_score_gemma":0.00006867739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001363068,"about_ca_topic_score_gemma":0.0001964175,"domain_scores_codex":[0.9981043,0.00003037066,0.0003677969,0.000208472,0.0010607,0.000228408],"domain_scores_gemma":[0.9977228,0.00007576917,0.000118951,0.0001527118,0.001914139,0.00001561125],"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":[0.0009143226,0.001437132,0.8231041,0.0002938673,0.00005195755,0.00003893834,0.0006585047,0.0003646168,0.00864228,0.004950678,0.05909339,0.1004501],"study_design_scores_gemma":[0.001961771,0.00002818702,0.3570695,0.0003281216,0.00001047473,0.000004869248,0.003542242,0.005880444,0.004343421,0.003465317,0.6229932,0.0003724486],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8189851,0.0001868947,0.0002271776,0.001462231,0.0005660492,0.0005179089,0.000005196011,0.00007677792,0.1779726],"genre_scores_gemma":[0.9982622,0.00002308963,0.0002039182,0.0001017243,0.0004871447,0.0001191343,0.00006762777,0.000017124,0.0007180068],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5638999,"threshold_uncertainty_score":0.4559157,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007331291,0.00007938365,0.0001170297,0.0005423485,0.0006011842,0.0001000218,0.0001671662,0.00005514432,0.0001636682],"category_scores_gemma":[0.0002310571,0.00007387305,0.000072581,0.0005824733,0.0001200344,0.001148311,0.00006475858,0.0001192931,0.0002007857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001330489,"about_ca_system_score_gemma":0.00009603782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002786983,"about_ca_topic_score_gemma":0.0001861491,"domain_scores_codex":[0.998814,0.00001535144,0.0002580006,0.000192103,0.0004471542,0.0002733192],"domain_scores_gemma":[0.9982676,0.00004248982,0.00002931991,0.0001911355,0.001453547,0.00001592936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003945354,0.001109016,0.01059691,0.0003870072,0.0001341038,0.000006559179,0.00156351,0.2232515,0.0265876,0.1075652,0.6142335,0.01417063],"study_design_scores_gemma":[0.0005020954,0.00003235436,0.00492594,0.00001899224,0.000008329276,0.000001630108,0.0002442741,0.975184,0.001554893,0.0007053192,0.01671143,0.0001107913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9392151,0.0001406656,0.01694457,0.006207443,0.0001820739,0.001337238,0.00007043,0.0001053123,0.0357972],"genre_scores_gemma":[0.9923441,0.0001251614,0.0005363298,0.0005294043,0.0004190851,0.0001357419,0.0001678655,0.0000167842,0.005725504],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7519325,"threshold_uncertainty_score":0.4623883,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000172435,0.0001401779,0.0001184107,0.0001097802,0.0001426498,0.0001566529,0.0001241686,0.00004300994,0.0009988181],"category_scores_gemma":[0.00001113462,0.00008961953,0.0000699114,0.0002969272,0.00002708772,0.0009677932,0.00009470858,0.0000642658,0.0007667957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003414196,"about_ca_system_score_gemma":0.000004941266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004276188,"about_ca_topic_score_gemma":0.00001923504,"domain_scores_codex":[0.9989872,0.00000868231,0.000225684,0.0002638981,0.0002237651,0.0002907826],"domain_scores_gemma":[0.9996504,0.00001792563,0.00009449611,0.0001598638,0.0000627535,0.0000145456],"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":[0.00003891541,0.0001261944,0.2532884,0.0001000389,0.00004652098,0.000004291238,0.00004674509,0.0002821274,0.0003771879,0.00376474,0.1583809,0.5835438],"study_design_scores_gemma":[0.004824224,0.0000409532,0.2265266,0.0003033206,0.0002349907,0.00002231769,0.0007298754,0.1393943,0.00004168568,0.0006697411,0.6258528,0.001359219],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3654368,0.0001969198,0.1433082,0.007433754,0.006626309,0.001235495,0.00001040546,0.001614694,0.4741375],"genre_scores_gemma":[0.9921299,0.000009935899,0.0001196063,0.002229663,0.003730619,0.00003584117,0.00003332054,0.00002027809,0.00169084],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6266931,"threshold_uncertainty_score":0.9999144,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004021019,0.0001183635,0.0001394165,0.0003358019,0.0001676511,0.0002010352,0.0003774993,0.0000885916,0.00004910383],"category_scores_gemma":[0.00003907465,0.0001099815,0.0000213253,0.000424454,0.00001884573,0.001048697,0.0002428638,0.0001012915,0.00003222933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001810231,"about_ca_system_score_gemma":0.00004566642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002870959,"about_ca_topic_score_gemma":0.00004468203,"domain_scores_codex":[0.9990391,0.000003291466,0.0002380249,0.0002914519,0.0002430801,0.00018501],"domain_scores_gemma":[0.9994566,0.00004320706,0.000154706,0.0002603408,0.00007363319,0.00001145988],"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":[0.001038816,0.0006610073,0.072283,0.004461689,0.000190362,0.00001720614,0.001523352,0.07790411,0.04302486,0.00148338,0.1305308,0.6668814],"study_design_scores_gemma":[0.0008301102,0.000002529311,0.007725523,0.0001151278,0.00003287496,1.052011e-7,0.00009721559,0.9834034,0.001023384,0.0002476746,0.006349148,0.0001728733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9795796,0.00000596808,0.01809814,0.0003138783,0.0003272741,0.0003730503,0.00002553787,0.0001107779,0.001165784],"genre_scores_gemma":[0.9971071,0.000002338377,0.001081946,0.001001189,0.0002150219,0.00003711409,0.0003458283,0.0000235131,0.000185923],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9054993,"threshold_uncertainty_score":0.4484915,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002238218,0.00008704936,0.00007693166,0.0006591875,0.0002068346,0.00008828175,0.00009201665,0.0000263694,0.000001134678],"category_scores_gemma":[0.000005866269,0.00005283195,0.00001631459,0.0005144891,0.00007948814,0.001190093,0.0001493445,0.00005688443,0.00005800493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001060515,"about_ca_system_score_gemma":0.000002025082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001015016,"about_ca_topic_score_gemma":0.000004608043,"domain_scores_codex":[0.9995464,0.000001849205,0.0001776695,0.00006346411,0.00007899877,0.0001316383],"domain_scores_gemma":[0.9997116,0.00001591522,0.0001224215,0.0001134879,0.00003315444,0.000003402771],"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":[0.00005644569,0.000008330977,0.001794709,0.0002904473,0.00005283215,4.568833e-7,0.00027584,0.002752527,0.00003874953,0.08561048,0.000799139,0.9083201],"study_design_scores_gemma":[0.002240291,0.0001640469,0.1355933,0.0003224085,0.00006393998,0.000004987401,0.01060718,0.67772,0.002077185,0.1329954,0.0376607,0.0005505424],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9925976,0.00004989287,0.001045918,0.0007402725,0.00007354662,0.0002461482,0.000001780654,0.0001778116,0.005067059],"genre_scores_gemma":[0.9983956,0.00122303,0.00002488931,0.0001729115,0.00001089714,0.00002820555,0.00001673221,0.000003696341,0.0001240298],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9077695,"threshold_uncertainty_score":0.2154424,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006926655,0.00009039889,0.00008847281,0.0002742289,0.001022872,0.0002112974,0.0002831331,0.00001760538,0.0002296339],"category_scores_gemma":[0.00001186297,0.00008027592,0.00004839762,0.0006751333,0.00007203475,0.00062194,0.0001689603,0.00006386911,0.00007772094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004764051,"about_ca_system_score_gemma":0.00002651125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000548176,"about_ca_topic_score_gemma":0.00004699154,"domain_scores_codex":[0.9988336,0.000002927788,0.0001935022,0.0002918061,0.0004658695,0.0002123244],"domain_scores_gemma":[0.9996932,0.00005306602,0.0001101128,0.00009611102,0.00003794772,0.000009598077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001867133,0.0001894862,0.00435573,0.00004884495,0.00001524444,8.701247e-7,0.0004056558,0.2868432,0.002721929,0.5626956,0.0291732,0.1133636],"study_design_scores_gemma":[0.0009080588,0.00005450529,0.002182671,0.00001032717,0.00005023233,0.000002378142,0.005301347,0.6558495,0.0003299247,0.1590927,0.175866,0.0003523251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.696148,0.00009265426,0.1705399,0.000700216,0.002124286,0.001600548,0.00001947929,0.000282139,0.1284927],"genre_scores_gemma":[0.9973435,0.00000388637,0.0007994813,0.001073693,0.0003162322,0.0002431974,0.00003997138,0.000009392304,0.0001706661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4036028,"threshold_uncertainty_score":0.7867209,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001104689,0.0001561897,0.0002842752,0.0004689023,0.0002652489,0.0002472381,0.0002723317,0.00008240853,0.0003687855],"category_scores_gemma":[0.0003159457,0.0001012067,0.0001866798,0.0005782261,0.00007427008,0.002517677,0.00006814385,0.0003983061,0.0001571198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001948897,"about_ca_system_score_gemma":0.00006786803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003617664,"about_ca_topic_score_gemma":0.00002885245,"domain_scores_codex":[0.9984891,0.00004039977,0.0005444243,0.0001287015,0.0005639828,0.0002334076],"domain_scores_gemma":[0.9980828,0.0001680468,0.001059632,0.000181644,0.0004841325,0.00002376093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009067204,0.0006592738,0.722883,0.001784856,0.001343595,0.00008218223,0.006445828,0.06093488,0.09529549,0.006915318,0.06478449,0.03796433],"study_design_scores_gemma":[0.008032883,0.0001663185,0.5243471,0.001893706,0.002175472,0.0002406915,0.08286463,0.3283151,0.001815929,0.005095668,0.0432753,0.001777276],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938962,0.0003977838,0.0003738181,0.002284536,0.000372485,0.0002360677,0.000001002046,0.00002372539,0.0024144],"genre_scores_gemma":[0.9973156,0.00001939061,0.0002909814,0.0001472831,0.0006657701,0.000004367031,0.00000433785,0.00002404412,0.001528228],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2673802,"threshold_uncertainty_score":0.4127091,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003565981,0.00006290314,0.0001587888,0.000387809,0.0007372648,0.0002508209,0.001144889,0.00004113182,0.00007020944],"category_scores_gemma":[0.0008286419,0.00004818185,0.00006551873,0.0007769141,0.0002987378,0.0008024293,0.0004784929,0.0001300581,0.00001516772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000196112,"about_ca_system_score_gemma":0.00003046133,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006930342,"about_ca_topic_score_gemma":0.007325412,"domain_scores_codex":[0.9988794,0.00004391124,0.0004042158,0.0002151245,0.0002638052,0.0001935674],"domain_scores_gemma":[0.9971836,0.0002794809,0.0003465453,0.001462625,0.0007194029,0.000008392408],"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":[0.0005540249,0.0005546355,0.02837654,0.0005581295,0.0009492694,0.00001034364,0.00231942,0.002858104,0.02778995,0.1167155,0.002457313,0.8168567],"study_design_scores_gemma":[0.00009316573,0.00005208976,0.007754191,0.00005431574,0.0005352063,0.000002544437,0.009900113,0.9414276,0.01246338,0.02547985,0.002102226,0.0001352613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9706493,0.00007649105,0.02114797,0.002955717,0.0001602008,0.001365981,0.0001886077,0.00002665226,0.00342906],"genre_scores_gemma":[0.9991555,0.00004808486,0.0002145136,0.00001598481,0.0001597026,0.00004463866,0.0003030238,0.000007325944,0.00005124772],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9385695,"threshold_uncertainty_score":0.9996826,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000159091,0.0001111799,0.0001125341,0.0001949033,0.00005530926,0.0001343883,0.0001039761,0.00003606786,0.0003142286],"category_scores_gemma":[0.000003940694,0.000103524,0.00005467511,0.0001766785,0.00001096495,0.0007326006,0.00003297851,0.00004106676,0.0001822493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006455876,"about_ca_system_score_gemma":0.000008636446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001079812,"about_ca_topic_score_gemma":0.0006668792,"domain_scores_codex":[0.9992312,0.000001876634,0.0002153164,0.0001952857,0.0001203725,0.0002359206],"domain_scores_gemma":[0.9997879,0.00001089787,0.00005952492,0.0001056197,0.00002782045,0.000008276072],"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":[0.0001676056,0.0007033285,0.004917657,0.0003143834,0.00005056861,0.000005806835,0.0004314019,0.4007576,0.0032331,0.05662208,0.06200128,0.4707952],"study_design_scores_gemma":[0.00121935,0.000008920612,0.0008856267,0.00001015126,0.00001769039,3.043829e-7,0.0004102555,0.9529787,0.0002060962,0.001970218,0.04208527,0.0002074077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7764187,0.0001398261,0.05626716,0.002164524,0.0001913805,0.001972233,0.000004498075,0.000256398,0.1625853],"genre_scores_gemma":[0.9897708,0.00001226724,0.001155217,0.002737047,0.0002846759,0.0002182512,0.00003749986,0.00001718136,0.005767062],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5522211,"threshold_uncertainty_score":0.4221586,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008212236,0.0001462808,0.0003188859,0.001172255,0.000180251,0.0002653996,0.0001521902,0.00003383887,0.00001865142],"category_scores_gemma":[0.0000430223,0.0001341587,0.0001184248,0.001197614,0.00003489583,0.0006147408,0.0003205171,0.0001648829,0.000002470349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005094018,"about_ca_system_score_gemma":0.00000820808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009415589,"about_ca_topic_score_gemma":0.0002484237,"domain_scores_codex":[0.9987568,0.00003387446,0.0005471985,0.0002143441,0.0002727241,0.0001750483],"domain_scores_gemma":[0.9992404,0.00004713689,0.0003848202,0.0002031422,0.0001047528,0.00001972334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001849211,0.0003789846,0.1068767,0.0001802864,0.0003004386,0.0001677474,0.0002157065,0.00385336,0.0000169232,0.00408108,0.0004350611,0.8833088],"study_design_scores_gemma":[0.00352043,0.00001746936,0.9181914,0.0001766788,0.002599067,0.00003559707,0.002506179,0.03584346,0.00001323068,0.01018187,0.02654258,0.0003720467],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7915772,0.001345945,0.2045556,0.0001037119,0.0001396596,0.0001790667,0.000001889575,0.00000801933,0.002088856],"genre_scores_gemma":[0.9511092,0.005440771,0.04274669,0.0004505873,0.0001757124,0.000005491641,0.00001295696,0.00001168378,0.00004688352],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8829368,"threshold_uncertainty_score":0.5470832,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006926913,0.0001045723,0.0001541758,0.0001106163,0.0001198827,0.0001573651,0.0002178162,0.00003192338,0.0006041257],"category_scores_gemma":[0.0000282342,0.00006901519,0.00008142182,0.0001198431,0.00004283429,0.0004860348,0.00003341672,0.000145443,0.00005144561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001661499,"about_ca_system_score_gemma":0.000006419559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000133526,"about_ca_topic_score_gemma":0.00002391217,"domain_scores_codex":[0.9993096,0.00002240128,0.0003181544,0.00006952704,0.0001444052,0.0001359222],"domain_scores_gemma":[0.9993988,0.0001058813,0.0002597746,0.00009332273,0.0001326465,0.000009558381],"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":[0.001652387,0.0002033976,0.009758567,0.0002963515,0.0002325855,0.000007500246,0.0015969,0.0003654439,0.001774455,0.01025345,0.1102395,0.8636194],"study_design_scores_gemma":[0.004635524,0.0002126971,0.06987134,0.0008095568,0.0009138297,0.0003298999,0.002339455,0.02432498,0.0004064236,0.00776045,0.8877516,0.0006442521],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9822038,0.0002418837,0.002836459,0.002731682,0.000356544,0.0001256029,7.038729e-7,0.00001886417,0.0114844],"genre_scores_gemma":[0.9943776,0.0001077035,0.00008987661,0.002687897,0.0006707249,0.000001765249,0.000004960098,0.00001462226,0.002044907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8629752,"threshold_uncertainty_score":0.6614752,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001288117,0.0001155294,0.000180223,0.0004175586,0.0006137697,0.0001373688,0.0001325195,0.00002777533,0.0002423933],"category_scores_gemma":[0.0001778376,0.0001090628,0.00009350591,0.0004370816,0.00001778397,0.0004155158,0.0002608653,0.0005027058,0.000005659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000608251,"about_ca_system_score_gemma":0.00001048266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009078919,"about_ca_topic_score_gemma":0.000006224658,"domain_scores_codex":[0.9988441,0.00004093421,0.0003859684,0.0001376454,0.0004235255,0.0001677813],"domain_scores_gemma":[0.9992789,0.00003471077,0.0005383787,0.00006784281,0.00006550852,0.00001467876],"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":[0.0004461732,0.0001455709,0.1221334,0.000153416,0.00004329081,0.0001064987,0.0005353422,0.002312741,0.00001739677,0.01027692,0.002346304,0.8614829],"study_design_scores_gemma":[0.001263981,0.0001092439,0.2200553,0.00007722421,0.0002515593,0.00002495929,0.001911307,0.004461573,0.000002762807,0.008194633,0.7634487,0.0001988051],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8911828,0.002452114,0.08641455,0.0007916655,0.003471285,0.0005038469,0.00001915419,0.0001077972,0.01505683],"genre_scores_gemma":[0.9962043,0.0007909587,0.001217761,0.0004994429,0.001088459,0.000009784731,0.000009590416,0.00001525251,0.0001644445],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8612841,"threshold_uncertainty_score":0.4720683,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001078379,0.0001607672,0.0001736595,0.0001425019,0.0002741358,0.0002723892,0.0001662218,0.0001120464,0.00001877022],"category_scores_gemma":[0.00003758389,0.0001601356,0.0000295674,0.001445487,0.0000389872,0.0003059113,0.0001899937,0.0005179682,0.00001917158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001882505,"about_ca_system_score_gemma":0.000008997547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001848517,"about_ca_topic_score_gemma":0.0000121789,"domain_scores_codex":[0.998877,0.00001317521,0.0003596798,0.0003634168,0.000141356,0.0002454107],"domain_scores_gemma":[0.9995015,0.00007847928,0.0001866832,0.0001094142,0.0001015211,0.00002236911],"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":[0.0001011159,0.0001019688,0.203969,0.00008720368,0.00001570351,0.00001036732,0.0003132797,0.1318869,0.001244659,0.009996487,0.001439558,0.6508337],"study_design_scores_gemma":[0.0002986535,0.00001207319,0.05622848,0.00002744623,0.00001007028,0.000002334005,0.0002624668,0.9416197,0.00001607723,0.0003717163,0.0009684167,0.0001825619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9667164,0.00002769706,0.02905148,0.002584453,0.0001009517,0.0005494544,0.000001443214,0.000151149,0.000816985],"genre_scores_gemma":[0.9943926,0.000001177599,0.0005571769,0.003632482,0.001325146,0.00003314999,0.00003524224,0.0000189077,0.000004067829],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8097328,"threshold_uncertainty_score":0.6530141,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001957819,0.000164668,0.0001209972,0.0004503316,0.0005351317,0.0005288266,0.0003018112,0.00002034932,0.0001786721],"category_scores_gemma":[0.00003198737,0.0001464757,0.0000410076,0.001223798,0.0001914244,0.002377656,0.0003914904,0.00007187678,0.0002052766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007494015,"about_ca_system_score_gemma":0.000002850745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004444204,"about_ca_topic_score_gemma":0.000005789305,"domain_scores_codex":[0.9981044,0.00001553699,0.0002317904,0.0003693222,0.0006890079,0.0005899284],"domain_scores_gemma":[0.9995285,0.00004127626,0.0001298295,0.0002302399,0.00002096873,0.00004921143],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003294005,0.0001625631,0.4091381,0.0001509464,0.00006061177,0.0000165153,0.0002954627,0.002653595,0.001474308,0.3408523,0.1378628,0.1072998],"study_design_scores_gemma":[0.0007742693,0.000006980682,0.8311517,0.00007739123,0.00009587927,0.000005364501,0.0004921519,0.01153945,0.00004728091,0.007074929,0.1482478,0.0004868344],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5681938,0.0001302495,0.3531264,0.01568492,0.003207503,0.001009349,0.000001118247,0.0002607659,0.0583859],"genre_scores_gemma":[0.84466,0.000009922453,0.06042835,0.093112,0.001472424,0.00003515818,0.00001371236,0.00002097496,0.0002474716],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4220136,"threshold_uncertainty_score":0.5973104,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004349532,0.0002558051,0.0003577714,0.0005973072,0.00004048777,0.0002371236,0.0003149925,0.0001629132,0.0009615221],"category_scores_gemma":[0.0001015835,0.0002617713,0.00008576882,0.0003479479,0.00003839645,0.001163256,0.00007913825,0.000233036,0.0007229157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008565131,"about_ca_system_score_gemma":0.0000395684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003151498,"about_ca_topic_score_gemma":0.0005667325,"domain_scores_codex":[0.998312,0.00002166338,0.0004436831,0.0005005294,0.0002920606,0.0004300747],"domain_scores_gemma":[0.9991747,0.00008744367,0.0002448233,0.0003719585,0.0000998647,0.00002123482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002940336,0.002648818,0.5484434,0.002141768,0.0002813576,0.0000683768,0.003269852,0.004264793,0.101906,0.02719651,0.1128944,0.1939444],"study_design_scores_gemma":[0.01363072,0.0003047056,0.4840984,0.002445244,0.0001774795,0.000007395679,0.002444799,0.4508136,0.001860124,0.009253287,0.0333533,0.001610909],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9867133,0.00007461233,0.0002381939,0.000919255,0.001163476,0.001016186,0.00005080831,0.0000992262,0.009724963],"genre_scores_gemma":[0.9878367,0.00002477068,0.0003090713,0.0005733648,0.0006493737,0.0000526998,0.0002816401,0.00003987915,0.0102325],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4465488,"threshold_uncertainty_score":0.9999834,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001537007,0.0001378521,0.000119344,0.000413441,0.0004879464,0.0004472571,0.0002795071,0.00002634361,0.0001559913],"category_scores_gemma":[0.000185591,0.00009161558,0.00006072557,0.001311524,0.0002032515,0.00297971,0.0001306912,0.00005958516,0.0007015655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000231654,"about_ca_system_score_gemma":0.00002080762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001339749,"about_ca_topic_score_gemma":0.0000380296,"domain_scores_codex":[0.9974224,0.00001014808,0.0002724735,0.0003986335,0.001473705,0.0004226559],"domain_scores_gemma":[0.9993044,0.00004829721,0.000173574,0.0002541633,0.0001930529,0.00002652313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00004744119,0.00001417293,0.07022123,0.000005814701,0.000005377681,0.000007581808,0.00002501524,0.00201942,0.5172605,0.0008601996,0.01625283,0.3932804],"study_design_scores_gemma":[0.00245186,0.00001540776,0.9279853,0.0003246782,0.00008104002,0.00002063319,0.0001991124,0.01792068,0.001955806,0.003063799,0.04494885,0.00103282],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.967262,0.00001207642,0.02644252,0.002961408,0.002147429,0.0001573699,3.60028e-7,0.0000759353,0.0009408786],"genre_scores_gemma":[0.988789,0.0000021924,0.001372412,0.008788606,0.001020391,0.000004530604,4.400054e-7,0.00001222817,0.00001019687],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8577641,"threshold_uncertainty_score":0.9017439,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003521146,0.0001506592,0.000150304,0.0003291699,0.0009823751,0.0003559393,0.0003609826,0.0001116956,0.0005502204],"category_scores_gemma":[0.00169155,0.00008724279,0.00007342309,0.0008792495,0.000277463,0.0005653509,0.0002080616,0.0006235087,0.0002335696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001840604,"about_ca_system_score_gemma":0.00005846825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003863975,"about_ca_topic_score_gemma":0.003812645,"domain_scores_codex":[0.9979408,0.0001297773,0.0003609128,0.0004218234,0.0006650565,0.0004816342],"domain_scores_gemma":[0.9979712,0.0008160918,0.0001079125,0.000308281,0.0007687511,0.00002778327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000438275,0.0007379484,0.3375542,0.00005673007,0.00008973114,0.000006525108,0.001043627,0.00004740656,0.006358735,0.01131941,0.001148649,0.6411988],"study_design_scores_gemma":[0.001357313,0.002170828,0.3638181,0.0006189328,0.0004869319,0.0000112361,0.1600787,0.0531284,0.1756312,0.1797971,0.06033449,0.002566702],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9590732,0.00004842755,0.01719443,0.01526286,0.0004652077,0.005257125,0.00002731807,0.0004416427,0.002229729],"genre_scores_gemma":[0.997899,0.00001440593,0.00003862259,0.0001057347,0.0007403886,0.0004196003,0.000007986191,0.00002569837,0.0007485424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6386321,"threshold_uncertainty_score":0.7555734,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002368893,0.0002418416,0.0001788337,0.0002653819,0.0005414205,0.0003102222,0.0001942722,0.0001338792,0.00004498913],"category_scores_gemma":[0.000005466176,0.0001911092,0.00003475985,0.0009813471,0.00006688291,0.001844733,0.00002108679,0.0001922753,0.0005698961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001225621,"about_ca_system_score_gemma":0.00001458133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001331496,"about_ca_topic_score_gemma":0.00001348724,"domain_scores_codex":[0.9985022,0.00002973245,0.0002781795,0.0004118569,0.0004179073,0.0003601569],"domain_scores_gemma":[0.9987825,0.0000267499,0.0003313884,0.0006290561,0.000172236,0.00005803235],"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":[0.0004682113,0.001261941,0.03840379,0.0003700146,0.0002310214,0.000001879215,0.002907493,0.001050723,0.007919285,0.9146498,0.01339622,0.01933965],"study_design_scores_gemma":[0.003380548,0.00011252,0.1271979,0.000587056,0.0006375329,0.0000753051,0.0379151,0.00500529,0.002052098,0.001309668,0.8193433,0.002383694],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0423129,0.0006877921,0.9093831,0.001839269,0.0007528742,0.004524868,0.000008078902,0.0007995465,0.03969154],"genre_scores_gemma":[0.9857398,0.00001173506,0.005875455,0.0001676244,0.002955434,0.004246822,0.0002888862,0.0000560966,0.0006580979],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.943427,"threshold_uncertainty_score":0.7793205,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001432484,0.0001362478,0.0001522386,0.001976647,0.0001165909,0.0004754477,0.0005384316,0.00003592826,0.0001905523],"category_scores_gemma":[0.00003596988,0.0001333743,0.00005280837,0.007100341,0.0001792417,0.00208423,0.0002577071,0.0001581881,0.000190564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001467169,"about_ca_system_score_gemma":0.000005883425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003487492,"about_ca_topic_score_gemma":0.0001046956,"domain_scores_codex":[0.9982002,0.00001130571,0.0002336305,0.0004321395,0.0007235563,0.000399163],"domain_scores_gemma":[0.9995168,0.000008377557,0.0001162996,0.0003011605,0.00002879038,0.00002851318],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001781059,0.00004678117,0.9705667,0.00002733659,0.00003324167,0.00004403012,0.00007544189,0.002552645,0.0001975534,0.001355865,0.02173921,0.003343324],"study_design_scores_gemma":[0.0005783543,0.00000212925,0.977535,0.00001400407,0.00007090486,2.676852e-7,0.0007697347,0.008966222,0.00001622828,0.0002065851,0.01162883,0.0002117265],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.900502,0.00000623021,0.0007423955,0.005652271,0.0003505748,0.0002083565,7.140635e-7,0.00006961244,0.09246781],"genre_scores_gemma":[0.9829035,0.000001529856,0.000306889,0.01601098,0.0001444643,0.00002127004,0.000007465653,0.000007650277,0.000596287],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09187152,"threshold_uncertainty_score":0.5438847,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00803528,0.00009526892,0.0001530643,0.0004551729,0.00015352,0.0002474228,0.0005334603,0.00002763626,0.00009883195],"category_scores_gemma":[0.0001875589,0.00005974845,0.00004354689,0.0003692008,0.00005841731,0.0003468696,0.0002536429,0.0002179845,0.00001431047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001431112,"about_ca_system_score_gemma":0.000009614267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003015238,"about_ca_topic_score_gemma":0.00001575854,"domain_scores_codex":[0.9984922,0.0001389965,0.0004161097,0.0001496108,0.0006409486,0.0001621776],"domain_scores_gemma":[0.9986445,0.0004655037,0.0003454791,0.0003411243,0.0001898155,0.00001354152],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0007334623,0.0002454172,0.005605554,0.0004423792,0.00008598638,0.00001164155,0.00004232291,0.0009018957,0.0001815253,0.01789445,0.03907565,0.9347797],"study_design_scores_gemma":[0.00387097,0.0005783307,0.3526194,0.00187894,0.0004144549,0.00000705707,0.01279912,0.2656811,0.000336405,0.0122456,0.3489744,0.0005941138],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7685249,0.0002747001,0.009995469,0.005599226,0.0007854121,0.0005839445,0.000001969652,0.00001744842,0.2142169],"genre_scores_gemma":[0.9984537,0.0001167543,0.0001115386,0.0004274326,0.0005346922,0.000001451778,0.000007135839,0.000009341506,0.0003379751],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9341856,"threshold_uncertainty_score":0.2784884,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003038355,0.0001017241,0.0001851402,0.0003342366,0.0001305696,0.00002727202,0.00006454184,0.00003268317,0.00002513072],"category_scores_gemma":[0.00001424663,0.00009746167,0.00009062029,0.0005148603,0.00002589848,0.001162049,0.000001537546,0.00006896335,0.000005067362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007163897,"about_ca_system_score_gemma":0.00003896194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001163872,"about_ca_topic_score_gemma":0.001115415,"domain_scores_codex":[0.9989108,0.000008011708,0.00059231,0.0001243846,0.0002359303,0.0001285993],"domain_scores_gemma":[0.9981462,0.00002913799,0.0009111413,0.00007664315,0.0008263877,0.00001052323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01253432,0.005797418,0.2054085,0.001565225,0.001158101,0.0002502603,0.03160456,0.04270351,0.3225674,0.01012378,0.00230016,0.3639867],"study_design_scores_gemma":[0.06931321,0.009064162,0.5152136,0.000361088,0.005707362,0.0008612204,0.2640029,0.01962822,0.05371897,0.01287123,0.04692925,0.002328797],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9330639,0.00002722093,0.06567048,0.00006742043,0.0003270106,0.0007453674,0.000002353188,0.00001552455,0.00008076674],"genre_scores_gemma":[0.9977258,0.000007896553,0.001487314,0.00008283693,0.0005739398,0.0000459774,0.00003162164,0.00001638083,0.0000282015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3616579,"threshold_uncertainty_score":0.3974372,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009856457,0.0001197655,0.0002398558,0.0003478474,0.00007305256,0.000066319,0.0002432347,0.00006097771,0.00002632941],"category_scores_gemma":[0.00009786904,0.0001168998,0.00002220878,0.0006211047,0.00002494046,0.001211671,0.0004698012,0.00008683388,6.227863e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005098352,"about_ca_system_score_gemma":0.00003002053,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01128582,"about_ca_topic_score_gemma":0.00225189,"domain_scores_codex":[0.9987012,0.00003455923,0.0005039671,0.0002453196,0.00033663,0.0001783369],"domain_scores_gemma":[0.9991945,0.00003388181,0.0003410798,0.0002805519,0.0001394563,0.00001054985],"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":[0.000500468,0.001347462,0.9618645,0.0001434747,0.00008629222,0.0004662589,0.0135908,0.0009169902,0.001553514,0.00003969483,0.003218871,0.01627168],"study_design_scores_gemma":[0.004722312,0.000112112,0.007411531,0.000228316,0.0001241963,0.00004413732,0.3415223,0.644935,0.0002099188,0.00002910453,0.000250166,0.0004109407],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9971414,0.00002511633,0.000924768,0.0000132996,0.0001273223,0.0003826211,0.000002490501,0.00004754424,0.001335465],"genre_scores_gemma":[0.9983886,0.000001090406,0.0009605048,0.0000883386,0.0004818263,0.000006108536,0.00002526083,0.0000186735,0.00002955487],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.954453,"threshold_uncertainty_score":0.9952981,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005364299,0.0001278672,0.0001950118,0.000410089,0.0001589306,0.0001732034,0.00009443193,0.00003184552,0.00001071728],"category_scores_gemma":[0.00001878699,0.0001004354,0.0000704161,0.001238142,0.00001243771,0.0002084889,0.00008980495,0.00006936284,0.00003292275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001906826,"about_ca_system_score_gemma":0.000004526762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001136349,"about_ca_topic_score_gemma":0.00001499747,"domain_scores_codex":[0.9989865,0.000003904452,0.0003601919,0.0001727212,0.0002121406,0.0002645555],"domain_scores_gemma":[0.9996364,0.00006931593,0.00008205593,0.0001325091,0.00005944431,0.00002031135],"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":[0.000003081681,0.000006560315,0.0003382103,0.0003578382,0.00009417127,4.103189e-7,0.0003863607,0.9906848,0.001928488,0.005362565,0.000008492498,0.0008289925],"study_design_scores_gemma":[0.0001137823,0.000003670339,0.0001232319,0.00005333014,0.0001848054,5.435227e-7,0.0006007323,0.9973835,0.0001676378,0.001049859,0.0001957429,0.0001232108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4266991,0.0000172787,0.5726749,0.00009881472,0.0000595059,0.0002125266,0.000001217902,0.0001139702,0.0001226375],"genre_scores_gemma":[0.9906052,0.00001342576,0.009152247,0.00002770874,0.00009311574,0.00003272109,0.00001235355,0.00002600819,0.0000372522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.563906,"threshold_uncertainty_score":0.4095637,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002729261,0.0002539206,0.0002493362,0.0007911524,0.00009979083,0.0003215277,0.0002537987,0.0001380684,0.0001005026],"category_scores_gemma":[0.00003703985,0.0002458989,0.00003673527,0.0004909007,0.0001858086,0.0009160138,0.0002475492,0.0003853846,0.00007312291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001399352,"about_ca_system_score_gemma":0.00004859107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008167529,"about_ca_topic_score_gemma":0.0003868504,"domain_scores_codex":[0.9983396,0.000005236746,0.000347811,0.0006383011,0.0004485537,0.000220505],"domain_scores_gemma":[0.9994755,0.0000454879,0.0002021146,0.0001726531,0.00008378451,0.00002040889],"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":[0.0000479495,0.00005614137,0.01017008,0.00029644,0.00001260108,0.00005585589,0.000596385,0.007107647,0.001406886,0.00258346,0.0001583085,0.9775082],"study_design_scores_gemma":[0.002510079,0.0001004345,0.0299775,0.001076541,0.00009578394,0.00002537931,0.00001591004,0.9106596,0.0003809243,0.03996603,0.01380767,0.001384193],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04795317,0.0008587934,0.9019494,0.007621168,0.004940529,0.002393375,0.00004633489,0.000482549,0.03375468],"genre_scores_gemma":[0.9726908,0.0001039783,0.0134361,0.009438363,0.003229305,0.00001446041,0.0003342431,0.00007076819,0.0006819303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.976124,"threshold_uncertainty_score":0.9999993,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002242704,0.0001094383,0.0001187955,0.0002038319,0.0000708583,0.00007801258,0.0006506033,0.00003572615,0.0001774048],"category_scores_gemma":[0.0002670647,0.0000937235,0.00002853613,0.0006060763,0.00002225074,0.0005517559,0.0002762225,0.00004891528,0.0005897957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000231082,"about_ca_system_score_gemma":0.000009989847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004605312,"about_ca_topic_score_gemma":0.0001329208,"domain_scores_codex":[0.9989761,0.000002454741,0.0003616736,0.0003120121,0.0001749137,0.0001728533],"domain_scores_gemma":[0.9989612,0.000136513,0.000102581,0.0006565563,0.000121927,0.00002124392],"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":[0.00004724954,0.0001445125,0.001421289,0.00008646847,0.00004632325,0.000001794018,0.0001298684,0.004289113,0.207759,0.06726491,0.002809171,0.7160003],"study_design_scores_gemma":[0.0001960736,0.00003525201,0.006279964,0.0006673302,0.00016343,0.000002219426,0.0007843309,0.4572423,0.2408888,0.0227288,0.2696211,0.001390345],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07532003,0.00004576597,0.9225578,0.001076494,0.0001478467,0.0003165849,0.00004000764,0.0001257807,0.0003696658],"genre_scores_gemma":[0.985538,0.000005788936,0.01342093,0.00009293947,0.0007297001,0.00007776575,0.00007186184,0.0000219332,0.00004110092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9102179,"threshold_uncertainty_score":0.7580827,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004478926,0.0001003779,0.0001734123,0.00005765496,0.0001293672,0.0001065085,0.0001768205,0.00004162409,0.00004474749],"category_scores_gemma":[0.0002398545,0.00009276594,0.00001969562,0.0002729401,0.00002997095,0.001486451,0.0003102114,0.0001307042,0.000002694653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000403505,"about_ca_system_score_gemma":0.00001373285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001120694,"about_ca_topic_score_gemma":0.00002259081,"domain_scores_codex":[0.9989991,0.00002052738,0.000267302,0.0003745613,0.0001999925,0.0001385231],"domain_scores_gemma":[0.9995103,0.00001760111,0.0001664948,0.0002138894,0.00006666403,0.00002505686],"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":[0.0002726216,0.0006506847,0.879333,0.002339423,0.0000703863,0.000007265303,0.002521703,0.005929385,0.05017467,0.00236855,0.0009167461,0.05541564],"study_design_scores_gemma":[0.0004225965,0.00002280608,0.001516351,0.00001020166,0.00005854674,0.000001648509,0.001046612,0.9928529,0.0000842476,0.0000896488,0.003754417,0.0001400208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9739065,0.00006549208,0.02046622,0.0003144162,0.00005774345,0.0002236466,0.000001337427,0.0001189172,0.004845747],"genre_scores_gemma":[0.9947953,0.000002225288,0.004373433,0.0002247731,0.0004089941,0.000002090781,0.000111983,0.00001436692,0.00006683635],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9869235,"threshold_uncertainty_score":0.3782885,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002789247,0.0001570279,0.00024256,0.0002135095,0.0001046779,0.0002169727,0.0002052704,0.00005716485,0.000117024],"category_scores_gemma":[0.0001366888,0.0001128627,0.00002857395,0.001199796,0.0000891382,0.001858932,0.000182584,0.000088772,0.00005812056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001448846,"about_ca_system_score_gemma":0.00002046167,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01834779,"about_ca_topic_score_gemma":0.0005893614,"domain_scores_codex":[0.9990286,0.00001135755,0.0003216847,0.0002014959,0.0002132053,0.0002236562],"domain_scores_gemma":[0.9989769,0.00008990023,0.0002127977,0.0001808291,0.0005308238,0.00000878921],"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":[0.00133051,0.0008999162,0.2684698,0.004132883,0.0001712799,0.0000280132,0.006349604,0.02989684,0.007956043,0.126674,0.001195609,0.5528955],"study_design_scores_gemma":[0.006220121,0.000004456735,0.1849271,0.0003731489,0.00009241103,0.00001866898,0.003239389,0.6362762,0.000198569,0.1663588,0.001724058,0.0005671323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9907843,0.000270876,0.0005773062,0.001660036,0.0001456859,0.0004712273,9.317374e-7,0.0000471154,0.006042484],"genre_scores_gemma":[0.9980028,0.00001566786,0.0001934669,0.001419314,0.0002124436,0.00006582266,0.00001752075,0.00002354018,0.00004941235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6063793,"threshold_uncertainty_score":0.9881891,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005321258,0.0002344393,0.0003101327,0.0006216713,0.0005085271,0.0003688976,0.0005928148,0.0001201538,0.00007214581],"category_scores_gemma":[0.0001221542,0.0001592256,0.0001185315,0.001005628,0.0001241133,0.0008740083,0.0001808712,0.0009446456,0.000006278995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001253464,"about_ca_system_score_gemma":0.0001110478,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008022504,"about_ca_topic_score_gemma":0.01684395,"domain_scores_codex":[0.9977304,0.0003571591,0.0008516285,0.0002315424,0.0004571362,0.0003721636],"domain_scores_gemma":[0.9982961,0.0001716595,0.000699919,0.0005856808,0.00019121,0.00005537332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001262531,0.001469473,0.4530393,0.002302198,0.001402288,0.005029222,0.002844939,0.01797434,0.001199832,0.01205654,0.03483346,0.4665858],"study_design_scores_gemma":[0.002508529,0.00006268526,0.9492474,0.0004453266,0.0009078068,0.0002921259,0.011895,0.001928449,0.00004232555,0.0003902882,0.031705,0.00057506],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9855695,0.0002016782,0.00003134615,0.00399616,0.0001615672,0.0007342144,0.00004929225,0.00001229758,0.009243945],"genre_scores_gemma":[0.9985965,0.00005380336,0.0001517082,0.0006479467,0.0004312089,0.00001396768,0.00004098497,0.00001495327,0.00004895592],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.496208,"threshold_uncertainty_score":0.9985831,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002437999,0.00040028,0.0004611105,0.001657992,0.0002593773,0.0005128754,0.0001317681,0.0001583993,0.006260093],"category_scores_gemma":[0.00000655741,0.0004119667,0.0002190981,0.0003766224,0.0000394636,0.0008624265,0.0002243933,0.0001754748,0.0002999333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001225931,"about_ca_system_score_gemma":0.00002903422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007715017,"about_ca_topic_score_gemma":0.008856338,"domain_scores_codex":[0.998204,0.000005323796,0.000609633,0.0005516339,0.0003764074,0.0002530283],"domain_scores_gemma":[0.9991165,0.00004213971,0.0004132959,0.0002424737,0.0001660341,0.00001949697],"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":[0.0002007096,0.0001037134,0.01685846,0.003969308,0.00982197,0.00007181794,0.001157864,0.0006587715,0.003995372,0.3674241,0.0471064,0.5486315],"study_design_scores_gemma":[0.006015902,0.00005766606,0.01029728,0.0008117533,0.03000379,0.00001038082,0.007575543,0.02785928,0.001602375,0.009395385,0.90117,0.005200679],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0004040603,0.000136007,0.04914188,0.0004225717,0.0004848676,0.0006585813,0.0000205613,0.0002257348,0.9485058],"genre_scores_gemma":[0.03334123,0.0003383328,0.004163647,0.006471664,0.001784853,0.00008136874,0.003166798,0.0001255847,0.9505265],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8540636,"threshold_uncertainty_score":0.9998332,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002976398,0.00006749792,0.00007836182,0.0001009775,0.0000569141,0.0001096892,0.00007937162,0.00002717151,0.0001214639],"category_scores_gemma":[0.00009704774,0.00005990049,0.00001968668,0.0001193537,0.00003156514,0.0001480495,0.00002940588,0.000048082,0.00003101248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009728547,"about_ca_system_score_gemma":0.000007756553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000178861,"about_ca_topic_score_gemma":0.000004408125,"domain_scores_codex":[0.9994119,0.000004217231,0.0002032845,0.0001743834,0.0001345221,0.00007169944],"domain_scores_gemma":[0.9996549,0.0001106212,0.00006189671,0.0001112681,0.00005644636,0.000004796938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003164962,0.0006691234,0.008031789,0.006537631,0.0001697526,0.000006887733,0.0007599911,0.002053073,0.04882326,0.1726691,0.4505061,0.3094567],"study_design_scores_gemma":[0.001152801,0.0000667948,0.0680569,0.0008360835,0.0001611924,0.000009331495,0.0006508804,0.7179564,0.0007618026,0.004304823,0.2057521,0.000290857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8986562,0.0003425815,0.09201127,0.003806448,0.001104894,0.000691695,0.0004904761,0.0001627967,0.00273367],"genre_scores_gemma":[0.9962516,0.000008216062,0.00197486,0.0001407345,0.0005438024,0.00002216745,0.000951667,0.00001079246,0.00009609199],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7159033,"threshold_uncertainty_score":0.2442671,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006886866,0.0001337,0.0001637054,0.0001959453,0.0005390167,0.0006121511,0.0002252348,0.00006136547,0.00005434578],"category_scores_gemma":[0.00008561824,0.0001260291,0.00004360584,0.00006620701,0.00003188823,0.002052744,0.00004124378,0.00006286336,0.00001065017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007845454,"about_ca_system_score_gemma":0.00002724804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003876623,"about_ca_topic_score_gemma":0.001973472,"domain_scores_codex":[0.9990672,0.000007786215,0.0002971415,0.0003537045,0.0001042453,0.0001699358],"domain_scores_gemma":[0.9992343,0.00009938713,0.0002792047,0.0002650087,0.0001110504,0.00001105831],"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":[0.002705593,0.0004944831,0.03669463,0.007958515,0.0001910781,0.000001998023,0.001018218,0.0004508172,0.03949987,0.05121381,0.01073735,0.8490337],"study_design_scores_gemma":[0.00309613,0.000007415708,0.008341959,0.0001181248,0.00005164617,6.654197e-7,0.002843838,0.9706488,0.00006628742,0.00006387734,0.014583,0.0001782136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02463791,0.000006706193,0.9569765,0.004563642,0.0007028346,0.001629884,0.00008814771,0.0000952675,0.01129912],"genre_scores_gemma":[0.9870752,0.000002293105,0.0103255,0.0003424669,0.0003937381,0.0001676893,0.001432476,0.00002402054,0.0002366299],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.970198,"threshold_uncertainty_score":0.5902987,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006295397,0.0002099844,0.0003164416,0.0005368047,0.000162353,0.0004378467,0.0001559571,0.00008237409,0.0002132174],"category_scores_gemma":[0.00008941523,0.0001670105,0.00005851026,0.0007392243,0.00004937094,0.001330422,0.000026069,0.0001718918,0.0001942508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001110211,"about_ca_system_score_gemma":0.00007100664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008711715,"about_ca_topic_score_gemma":0.0005170808,"domain_scores_codex":[0.9982046,0.00001760848,0.0006087956,0.0004470878,0.0004339715,0.0002878599],"domain_scores_gemma":[0.9991945,0.0001144157,0.0001849369,0.0002297053,0.0002602431,0.0000161738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001214926,0.0002531681,0.9325889,0.0004676856,0.00009365482,0.00007061305,0.0008539825,0.0005437804,0.001425455,0.001494839,0.01118814,0.04980483],"study_design_scores_gemma":[0.006168887,0.0000889884,0.933193,0.001479663,0.0001371783,0.00002735473,0.007258043,0.01119552,0.0003482045,0.0003708895,0.03917772,0.0005546072],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9428058,0.0001172084,0.01164764,0.0001911404,0.001460995,0.001221573,0.000022031,0.0001247368,0.04240889],"genre_scores_gemma":[0.9963744,0.000007191797,0.00005187287,0.0002505547,0.0003400189,0.0000877979,0.0001340087,0.00002050846,0.002733692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05356856,"threshold_uncertainty_score":0.681049,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004450944,0.0000843918,0.00008570677,0.0001832916,0.0005895533,0.0004242436,0.0003295045,0.00003356147,0.0001085333],"category_scores_gemma":[0.00002121933,0.00007821678,0.00003849429,0.0009884948,0.0001601717,0.0009464541,0.00007793511,0.00006518363,0.0005031912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004697631,"about_ca_system_score_gemma":0.00001913767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001444791,"about_ca_topic_score_gemma":0.000105869,"domain_scores_codex":[0.9989839,0.000006083772,0.0001136452,0.000233714,0.0004100112,0.0002526547],"domain_scores_gemma":[0.9996792,0.00000848499,0.0001096685,0.0001140576,0.00007137263,0.00001720812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002942803,0.0002199638,0.03236347,0.0001877409,0.00001561483,0.000006118171,0.006177627,0.00002312741,0.003518658,0.1104162,0.002528176,0.8445138],"study_design_scores_gemma":[0.001079203,0.00008877958,0.7561927,0.00007737247,0.00006732388,0.000001516902,0.0145786,0.004844881,0.0008995882,0.01193856,0.2093557,0.0008757916],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3979018,0.00000196802,0.00004641523,0.0005282916,0.0002830489,0.0001313515,7.558472e-7,0.00008627726,0.60102],"genre_scores_gemma":[0.9961679,5.644041e-7,0.00002963696,0.002576796,0.0009920297,0.000008347544,0.000006649469,0.000006929386,0.0002111668],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8436381,"threshold_uncertainty_score":0.6467673,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000443813,0.0001123712,0.0001949201,0.0003975384,0.0000994647,0.0001300586,0.00008047537,0.00004696069,0.00002480345],"category_scores_gemma":[0.0001876107,0.0001019343,0.00004617201,0.0006723268,0.0000140546,0.0004567992,0.00008814201,0.0001798964,0.00000209109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005646433,"about_ca_system_score_gemma":0.00002337507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001986699,"about_ca_topic_score_gemma":0.00003294066,"domain_scores_codex":[0.9991405,0.0000180059,0.0003445892,0.0001504151,0.0002172751,0.0001292069],"domain_scores_gemma":[0.9993498,0.00002503238,0.0003431395,0.00007694255,0.0001937596,0.00001130293],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0006009855,0.0006629596,0.05415496,0.000369639,0.00009943749,0.0002377258,0.002316588,0.05370738,0.003992834,0.07649019,0.001199645,0.8061677],"study_design_scores_gemma":[0.007046305,0.00008213771,0.8520683,0.0005011885,0.0005055078,0.00003498996,0.002330689,0.07496525,0.0007776318,0.04920858,0.01194209,0.0005373239],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2719005,0.0001313617,0.7253548,0.0001506171,0.0004336364,0.0001371301,0.000003185243,0.00001241717,0.001876416],"genre_scores_gemma":[0.9695764,0.0003224021,0.02882159,0.0007548658,0.0004420001,0.000002244434,0.000008536063,0.00001640957,0.00005553594],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8056303,"threshold_uncertainty_score":0.4156761,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004242375,0.0001351692,0.0001891911,0.000227864,0.000130716,0.0001524311,0.000257358,0.00003576814,0.0003151685],"category_scores_gemma":[0.00002251368,0.0001299715,0.00002546818,0.0004054208,0.00001315192,0.001633724,0.0004132003,0.00008148679,0.0000267069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002432786,"about_ca_system_score_gemma":0.00001156914,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008999793,"about_ca_topic_score_gemma":0.0004222337,"domain_scores_codex":[0.998798,0.00001171072,0.0003477903,0.0003467849,0.0002923093,0.0002034741],"domain_scores_gemma":[0.999174,0.00003385068,0.0002755305,0.0004343517,0.000072918,0.000009375763],"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":[0.00001450893,0.0002797839,0.9909902,0.00008131634,0.00004432298,0.0001332223,0.0009425827,0.0001674995,0.002633536,0.00001484253,0.0008731225,0.003825114],"study_design_scores_gemma":[0.006329098,0.000112518,0.009012084,0.0001917894,0.0009635016,0.0003830722,0.4550698,0.5257094,0.0002387952,0.000006626065,0.001001915,0.0009814454],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9942886,0.00001429721,0.00008965196,0.00001053141,0.0002969891,0.0004230037,0.000005346208,0.00007267909,0.004798851],"genre_scores_gemma":[0.9992417,3.617164e-7,0.0002323717,0.000127986,0.000148228,0.000002678765,0.00006773477,0.00002359341,0.0001554056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9819781,"threshold_uncertainty_score":0.9975994,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004552544,0.0001033947,0.00009552021,0.0001459301,0.00162275,0.001255958,0.0003087204,0.00005175748,0.00002421109],"category_scores_gemma":[0.00004618718,0.0001016179,0.0000230664,0.0001181663,0.0002533905,0.001290997,0.0001266165,0.0001101909,0.00006546779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003531858,"about_ca_system_score_gemma":0.00001896801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006807039,"about_ca_topic_score_gemma":0.00001682486,"domain_scores_codex":[0.9989692,0.00000207348,0.0001335936,0.0003724594,0.0002866306,0.000236061],"domain_scores_gemma":[0.9993982,0.00001604639,0.000201914,0.0002694506,0.00009604776,0.00001832937],"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":[0.00005594755,0.00008486277,0.03569165,0.00008414745,0.000004017065,8.473207e-7,0.00067731,0.00004706406,0.3892542,0.06562694,0.00007960319,0.5083934],"study_design_scores_gemma":[0.001295367,0.00002070053,0.3777266,0.00005832866,0.0000736427,0.000001122485,0.001151295,0.5739271,0.0017186,0.04133269,0.002139267,0.000555319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6604234,0.000007466394,0.3328006,0.0004859662,0.0001898746,0.0003705888,0.000001303918,0.0000822239,0.005638575],"genre_scores_gemma":[0.9978875,0.000002735705,0.001275189,0.0004129849,0.0002651884,0.00005928809,0.00001804618,0.00001378934,0.00006527385],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5738801,"threshold_uncertainty_score":0.9997808,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004282294,0.0001686248,0.0001669604,0.0001562309,0.001239404,0.0001722522,0.000168774,0.00003287278,0.0002960296],"category_scores_gemma":[0.00001316011,0.0001713964,0.00007160038,0.0007561633,0.00004213007,0.0004200668,0.0001710041,0.0002794942,0.0000474068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001535099,"about_ca_system_score_gemma":0.0000235873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000301635,"about_ca_topic_score_gemma":0.00002735723,"domain_scores_codex":[0.9986458,0.00002256001,0.0003490146,0.0003287087,0.0002998344,0.0003540446],"domain_scores_gemma":[0.9994907,0.00001897869,0.0002689124,0.0001354561,0.00007183856,0.0000140641],"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":[0.00008263157,0.00008072629,0.002267174,0.00004506029,0.00002493616,0.000005269019,0.0003955287,0.9863371,0.003259772,0.0007031183,0.0004898712,0.006308794],"study_design_scores_gemma":[0.0001080614,0.00005322062,0.0000650837,0.00001800898,0.0000579218,0.000005379909,0.001546739,0.9952749,0.0004292546,0.0003836259,0.001860498,0.0001973155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8826431,0.00006132401,0.113283,0.0003743979,0.0004672545,0.0005351042,0.000009731873,0.0006820893,0.00194404],"genre_scores_gemma":[0.9976562,0.000004399007,0.0008390172,0.0004850226,0.0003140533,0.00005825088,0.0001300792,0.0000363572,0.0004766457],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1150131,"threshold_uncertainty_score":0.9532621,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001959665,0.00008412499,0.000109395,0.00011782,0.0001966017,0.00007971212,0.0001074766,0.0000310593,0.001085906],"category_scores_gemma":[0.00003415924,0.00007331236,0.00004483718,0.00021172,0.00007204922,0.000609919,0.00001060227,0.00002976888,0.00009958243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001232525,"about_ca_system_score_gemma":0.00001546457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008698566,"about_ca_topic_score_gemma":0.0009322913,"domain_scores_codex":[0.9993437,0.000004025604,0.0002291961,0.0001574904,0.0001274903,0.000138093],"domain_scores_gemma":[0.9995508,0.00003232467,0.0001232015,0.0001316795,0.0001546191,0.000007386149],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002944399,0.0004468882,0.002041495,0.001483476,0.0002247872,0.000005215348,0.0007472503,0.001441716,0.4806823,0.05925678,0.1540115,0.2993641],"study_design_scores_gemma":[0.005147215,0.0002019704,0.00447197,0.000243434,0.001053178,0.00001402334,0.005547451,0.4523626,0.07885465,0.003606353,0.4467081,0.001789095],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2103385,0.00005935852,0.7440263,0.00146979,0.001402177,0.0009940253,0.0007867431,0.0002758903,0.04064724],"genre_scores_gemma":[0.9894397,0.000003061821,0.007480358,0.0008703705,0.0007061125,0.00002437091,0.0005308665,0.00001264989,0.0009324942],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7791013,"threshold_uncertainty_score":0.9998273,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008271182,0.0001449571,0.000145436,0.0001950664,0.0002528067,0.0004832016,0.0001600234,0.00004441218,0.0003783514],"category_scores_gemma":[0.0002812655,0.000128455,0.00001784512,0.0002826927,0.00004406785,0.001372544,0.0004558437,0.0000845648,0.00003849961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003120076,"about_ca_system_score_gemma":0.000006807702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001183801,"about_ca_topic_score_gemma":0.00002380814,"domain_scores_codex":[0.9990174,0.00002560862,0.0002142359,0.0003516595,0.0001510094,0.0002401326],"domain_scores_gemma":[0.9993433,0.0001350018,0.0001592899,0.0002297673,0.0001193362,0.00001330603],"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":[0.00004699024,0.0001039371,0.04706452,0.0003705782,0.00007600015,0.000007833553,0.0003093302,0.00009565333,0.1715856,0.000365153,0.007087362,0.7728871],"study_design_scores_gemma":[0.0009313238,0.00001055702,0.02594909,0.0002619153,0.000134423,0.00001516987,0.0096969,0.9469536,0.006305492,0.00007509878,0.008911037,0.0007554264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9832053,0.0000659885,0.002963143,0.0001678275,0.0001596729,0.001439218,0.00000174086,0.00024258,0.01175448],"genre_scores_gemma":[0.9875863,0.000002319749,0.01106914,0.0007048447,0.0003834873,0.00006690259,0.00006921327,0.00002412893,0.00009362079],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9468579,"threshold_uncertainty_score":0.5238241,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007635005,0.00004932972,0.00005324163,0.0001822384,0.0005761569,0.000967379,0.0005846641,0.00001267529,0.00003181359],"category_scores_gemma":[0.00006162251,0.00002024647,0.00004146682,0.0008641636,0.000166976,0.01143934,0.00004794109,0.00007572417,0.000001435963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001306772,"about_ca_system_score_gemma":0.0003628273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003962419,"about_ca_topic_score_gemma":0.001246073,"domain_scores_codex":[0.9992279,0.000007878656,0.0003905332,0.00002664803,0.0002495263,0.00009748741],"domain_scores_gemma":[0.9992157,0.00006673024,0.0004430611,0.0001194224,0.0001362397,0.00001882271],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001780718,0.00003122538,0.5954515,0.00159942,0.0001269377,0.000001145451,0.04133093,0.001944398,0.00009407648,0.1009599,0.08337776,0.1749046],"study_design_scores_gemma":[0.0004058987,0.00003140407,0.5598661,0.000155416,0.00004703469,0.00001091161,0.03999033,0.04323885,0.00006660286,0.0009595483,0.3551463,0.00008158648],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.984641,0.0003871581,0.0001000146,0.008350063,0.001202145,0.0005645452,0.00001550788,0.000005905261,0.00473362],"genre_scores_gemma":[0.9983762,0.00001909226,0.00001416189,0.001435551,0.00006096786,0.0000026528,0.000001222595,0.000001663462,0.00008846923],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2717685,"threshold_uncertainty_score":0.9328458,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003188156,0.0001490321,0.0001355604,0.0002033184,0.0003127471,0.001013959,0.0002084132,0.00005552135,0.00006892334],"category_scores_gemma":[0.00004632306,0.0001351231,0.00001607564,0.0001193549,0.00004827647,0.001756657,0.00007763572,0.00006928456,0.0000265515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002364751,"about_ca_system_score_gemma":0.00004142674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001431993,"about_ca_topic_score_gemma":0.001947628,"domain_scores_codex":[0.9990427,0.000007677868,0.0004271076,0.0001722971,0.0002059413,0.000144297],"domain_scores_gemma":[0.9991527,0.00006041376,0.0001607398,0.0001469237,0.0004645777,0.0000146721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001732551,0.0002796652,0.003695258,0.0007625431,0.0001570746,0.000003259286,0.00221544,0.03359405,0.003782796,0.8449163,0.0164081,0.09401231],"study_design_scores_gemma":[0.0005950293,0.00001606526,0.0004336059,0.00005171586,0.00005015345,0.000004720897,0.004041836,0.983005,0.00006411228,0.001465823,0.01007308,0.0001987914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07461493,0.00004620847,0.8573959,0.005427522,0.001294409,0.0008681182,0.0005734507,0.0001151713,0.05966423],"genre_scores_gemma":[0.8478928,0.0001279782,0.1368347,0.008599065,0.001308697,0.0000575458,0.004438199,0.00002329424,0.0007177086],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.949411,"threshold_uncertainty_score":0.9777632,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001112363,0.0001376827,0.0001343562,0.0002388972,0.0002012884,0.0003245463,0.00006526461,0.00004611551,0.0001762327],"category_scores_gemma":[0.000005233775,0.000125847,0.00004411238,0.0003075972,0.00002442229,0.0006426385,0.00008145978,0.00004138885,0.00007341019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009375664,"about_ca_system_score_gemma":0.00003252578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001137591,"about_ca_topic_score_gemma":0.00005827418,"domain_scores_codex":[0.9992155,0.000005770687,0.0002180076,0.0002433869,0.000132962,0.0001843181],"domain_scores_gemma":[0.9996919,0.00001903466,0.00007973114,0.00009643352,0.0001028118,0.00001008511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000146587,0.0006222012,0.1816791,0.0007793784,0.0003732182,0.000004460003,0.00009341819,0.0007511613,0.01646041,0.2363818,0.5418134,0.02089489],"study_design_scores_gemma":[0.004808101,0.00002587979,0.1570913,0.0000579806,0.00036203,0.000001538889,0.0008233954,0.7184774,0.001592281,0.001677748,0.1145579,0.0005244639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.676935,0.0001047725,0.109279,0.01471581,0.002906214,0.004829633,0.00002527468,0.002605927,0.1885983],"genre_scores_gemma":[0.990994,0.00000645345,0.001198316,0.004778892,0.000136651,0.00008834451,0.0004045129,0.000014581,0.002378202],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7177262,"threshold_uncertainty_score":0.513189,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0119676,0.0001854837,0.0002725692,0.0004490547,0.0008009878,0.0002035774,0.0003346996,0.00008585712,0.0000865858],"category_scores_gemma":[0.0005696641,0.0001574886,0.00009578155,0.0009407722,0.000048418,0.0001650203,0.0002844635,0.0002958286,0.00003496281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001199034,"about_ca_system_score_gemma":0.00009353892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004888207,"about_ca_topic_score_gemma":0.0001202994,"domain_scores_codex":[0.9978014,0.0001035127,0.0005302277,0.0003668848,0.0006736963,0.0005242953],"domain_scores_gemma":[0.9974392,0.001710934,0.0002424945,0.0001939571,0.0003923604,0.00002104451],"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":[0.01115308,0.0008251055,0.05831091,0.008319338,0.0005386967,0.000001923164,0.0151206,0.3455197,0.1256123,0.01477612,0.006795889,0.4130263],"study_design_scores_gemma":[0.0009581618,0.00000526017,0.002846967,0.0001713875,0.00007390345,1.471159e-7,0.009883714,0.9764258,0.0005034098,0.0004961886,0.00832447,0.0003105907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9578411,0.00002454422,0.02120641,0.0004285311,0.000159714,0.0009629268,0.000003626302,0.00007378705,0.01929937],"genre_scores_gemma":[0.9875111,0.000001801938,0.01166347,0.0001928736,0.0003593142,0.00003270785,0.00006387573,0.00005182688,0.0001230282],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.630906,"threshold_uncertainty_score":0.6422199,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001337244,0.0001728726,0.0002513752,0.0007937849,0.000481669,0.0008088177,0.0003370649,0.00007417909,0.00004179173],"category_scores_gemma":[0.0003483522,0.0001492641,0.00006537705,0.00090304,0.00003436644,0.001457053,0.0004905628,0.0003942552,0.00002798616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001089761,"about_ca_system_score_gemma":0.00005209031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006886195,"about_ca_topic_score_gemma":0.00001486549,"domain_scores_codex":[0.9983328,0.00003657117,0.0005239222,0.0003924705,0.0004851339,0.0002291081],"domain_scores_gemma":[0.9990864,0.00006407465,0.0002162735,0.0003143816,0.0002681461,0.00005066935],"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":[0.0002120913,0.0002504398,0.02015739,0.00008700285,0.0001343753,0.000007574732,0.0001271307,0.9313836,0.0002891196,0.006564963,0.005851855,0.03493451],"study_design_scores_gemma":[0.000622782,0.00000720359,0.002536557,0.0000823981,0.0001916329,0.0000213544,0.0001374995,0.9791563,0.00000230813,0.007052919,0.01005707,0.0001320347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1695011,0.0001517981,0.821016,0.0003468368,0.0003669318,0.0003063523,0.00001608394,0.000063003,0.008231937],"genre_scores_gemma":[0.9609544,0.00007005552,0.03678164,0.001169488,0.0005489215,0.00000292859,0.0001062214,0.00002573473,0.0003406281],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7914533,"threshold_uncertainty_score":0.7799448,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001691799,0.0001508947,0.0001648968,0.0001700299,0.0002631365,0.0005370492,0.0001505667,0.00006077181,0.0004024098],"category_scores_gemma":[0.00002430674,0.0001666765,0.0000865592,0.0005596633,0.00002091183,0.002049056,0.00001785655,0.00008920438,0.00003573387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001139404,"about_ca_system_score_gemma":0.00005671301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009752944,"about_ca_topic_score_gemma":0.001126053,"domain_scores_codex":[0.9990388,0.00001285924,0.0002558386,0.000295993,0.0001590321,0.0002374928],"domain_scores_gemma":[0.9993681,0.00004175856,0.0001831626,0.0001453649,0.0002475617,0.00001408152],"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":[0.0007419196,0.0006014664,0.1380141,0.002760343,0.0002189364,0.00003474644,0.0002893082,0.1691512,0.1524415,0.0004104818,0.008053361,0.5272827],"study_design_scores_gemma":[0.006246892,0.00001438896,0.03935769,0.0004494848,0.0003110473,0.000009860478,0.0004496527,0.7171359,0.09654389,0.0004713172,0.1375729,0.001436989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6964504,0.00006930765,0.2952187,0.001313034,0.003283269,0.0004145756,0.00002416568,0.0001654561,0.003061154],"genre_scores_gemma":[0.9958247,0.00001276715,0.0005780369,0.002387838,0.0008770477,0.00004776873,0.0001450214,0.00003322437,0.00009359785],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5479847,"threshold_uncertainty_score":0.6796869,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002794985,0.0001206933,0.00009450785,0.000133122,0.0002064601,0.0005362075,0.0000660518,0.00005922801,0.0004292762],"category_scores_gemma":[0.00005363137,0.0001083831,0.00009827298,0.000337814,0.00002059916,0.001130681,0.00004052343,0.0001100821,0.0009146721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000668822,"about_ca_system_score_gemma":0.00001840387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007668093,"about_ca_topic_score_gemma":0.000003696309,"domain_scores_codex":[0.9991726,0.000005334328,0.0001945247,0.0002510599,0.0001729708,0.0002035545],"domain_scores_gemma":[0.9997607,0.00003821211,0.00004322647,0.00006943522,0.00007751511,0.00001088219],"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":[0.0002668727,0.00021111,0.008171993,0.001547122,0.0002323003,0.00001582161,0.000285804,0.02247747,0.007680233,0.5305296,0.3254204,0.1031612],"study_design_scores_gemma":[0.0003064135,0.00001411335,0.002240926,0.00004119123,0.00009228278,0.000002034813,0.0002239475,0.4203879,0.0002056311,0.0002572174,0.5760804,0.0001478516],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.235262,0.0004289272,0.6554989,0.003749247,0.004403352,0.001526416,0.00009354534,0.003098202,0.09593944],"genre_scores_gemma":[0.9883319,0.000009523464,0.0003503578,0.0002834805,0.001939761,0.00005760124,0.001678141,0.00002901222,0.007320241],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7530699,"threshold_uncertainty_score":0.9998632,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}