{"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,"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","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"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"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.178961144832458,"score_gpt":0.3436977908249927,"score_spread":0.1647366459925347,"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."}}