{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001485151,0.0006819668,0.001009786,0.00115015,0.0005428932,0.001602791,0.001762176,0.001540392,0.002055102],"category_scores_gemma":[0.002747771,0.0005616904,0.001067181,0.001333654,0.000740156,0.001888859,0.00104735,0.001647678,0.0005879421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001749199,"about_ca_system_score_gemma":0.001394481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01794552,"about_ca_topic_score_gemma":0.009808973,"domain_scores_codex":[0.9992761,0.0001528715,0.00005496906,0.0001895833,0.0001894445,0.0001371679],"domain_scores_gemma":[0.9988901,0.0005644968,0.0001584717,0.00004350198,0.0002858053,0.00005764681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008569894,0.0000794658,0.003760209,0.0000657666,0.00004813432,0.000185561,0.000173385,0.9523193,0.001322596,0.01288296,0.001091807,0.02798519],"study_design_scores_gemma":[9.934366e-7,0.000005622301,0.0001412403,0.000002111587,0.000003710504,0.000008564184,0.000004441603,0.9987766,0.00005412333,0.0009098616,0.00009000846,0.000002663988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07030178,0.0006753193,0.9205706,0.0006903896,0.00006236089,0.0001167363,0.0002792591,0.0005923213,0.006711307],"genre_scores_gemma":[0.9394551,0.0006457065,0.05325421,0.0001638465,0.00006793408,0.0002090941,0.0004192465,0.0000684558,0.005716258],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01794552,"threshold_uncertainty_score":0.03568214,"prediction_status":"machine_predicted_unvalidated"},"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."}}