{"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,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Feature selection; Computer science; Data mining; Random forest; Feature (linguistics); Machine learning; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"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"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4113565419835101,"score_gpt":0.4777785203359856,"score_spread":0.06642197835247554,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}