{"id":"W4413181102","doi":"10.1109/netcrypt65877.2025.11102705","title":"Predictive Analytics for Customer Retention: A CatBoost Model for Churn Detection","year":2025,"lang":"en","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Analytics; Predictive analytics; Data science; Machine learning","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":[0.001878004,0.0008711473,0.001135582,0.001263001,0.0007316059,0.001306087,0.002240898,0.001441145,0.002264607],"category_scores_gemma":[0.003318988,0.000485547,0.001096884,0.001602655,0.000535634,0.0009484582,0.0007081426,0.002349059,0.0008501787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001439907,"about_ca_system_score_gemma":0.001854972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02174565,"about_ca_topic_score_gemma":0.02113561,"domain_scores_codex":[0.9993749,0.0001727674,0.00003353547,0.0001387595,0.0001719587,0.0001081763],"domain_scores_gemma":[0.9985367,0.0006894289,0.0001226381,0.00007028785,0.0005028698,0.00007803563],"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":[0.0004206177,0.000476282,0.009432214,0.000203973,0.0001821437,0.000116375,0.0001383441,0.7572907,0.002790176,0.005105592,0.007476132,0.2163675],"study_design_scores_gemma":[0.00000477563,0.00003544518,0.0004562046,0.00001076759,0.000007681658,0.00001201371,0.00001063706,0.9977757,0.0002966954,0.0009883745,0.0003957336,0.000005882647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1150555,0.001288901,0.8732417,0.001209536,0.0003291072,0.0003294708,0.0006047963,0.002617387,0.005323517],"genre_scores_gemma":[0.795872,0.0005799477,0.1923543,0.0005652936,0.0001391078,0.000443907,0.001332377,0.0002258438,0.008487293],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02174565,"threshold_uncertainty_score":0.04323816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03357122463854333,"score_gpt":0.2681094132389699,"score_spread":0.2345381886004265,"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."}}