{"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,"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","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":[0.000443813,0.0001123712,0.0001949201,0.0003975384,0.0000994647,0.0001300586,0.00008047537,0.00004696069,0.00002480345],"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"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0126362890742379,"score_gpt":0.2535957041644796,"score_spread":0.2409594150902417,"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."}}