{"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,"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","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":[0.003121207,0.001199217,0.001865041,0.001430435,0.001284933,0.001760487,0.003021204,0.002424039,0.01035937],"category_scores_gemma":[0.006280265,0.001023134,0.001217104,0.002012624,0.0007382238,0.002853242,0.001086744,0.003610781,0.002809532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001799015,"about_ca_system_score_gemma":0.001808573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02657054,"about_ca_topic_score_gemma":0.03564094,"domain_scores_codex":[0.9991282,0.0004307673,0.00005007982,0.0001719664,0.0001042981,0.0001147529],"domain_scores_gemma":[0.9941096,0.004541791,0.000229072,0.0003396501,0.0006167541,0.0001631675],"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":[0.0005473936,0.0003228479,0.005616809,0.0001140207,0.0001117913,0.00011994,0.00008085359,0.8788134,0.0003302783,0.01265477,0.01016659,0.09112131],"study_design_scores_gemma":[0.00001186809,0.00001507459,0.0002025603,0.000005095626,0.000009074923,0.000006577887,0.000005600812,0.9945837,0.00007994012,0.004621037,0.0004542315,0.000005249308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2691292,0.003627487,0.6990104,0.004523357,0.0006170642,0.0001678875,0.01033159,0.004652892,0.007940315],"genre_scores_gemma":[0.8874673,0.001109823,0.07543097,0.000615949,0.0003895561,0.0003731074,0.008595943,0.0003112394,0.02570608],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02657054,"threshold_uncertainty_score":0.05283177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4472177535679772,"score_gpt":0.4369719839560914,"score_spread":0.01024576961188572,"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."}}