{"id":"W7125446432","doi":"10.18280/mmep.121226","title":"Explainable Customer Churn Prediction in Telecom Using Ensemble Learning and SHAP Analysis","year":2025,"lang":"","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Ensemble learning; Ensemble forecasting; Key (lock); Training set","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001118466,0.000697432,0.0007374469,0.001416685,0.0003241749,0.00076628,0.0006964234,0.0007040466,0.0007893633],"category_scores_gemma":[0.003104331,0.0002446889,0.0007780641,0.001027333,0.0002049035,0.001026759,0.0005948512,0.000938839,0.0002028647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007265921,"about_ca_system_score_gemma":0.000604476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01033839,"about_ca_topic_score_gemma":0.01438351,"domain_scores_codex":[0.9996272,0.00009918432,0.00002089952,0.00008757244,0.00008604972,0.0000791483],"domain_scores_gemma":[0.9983807,0.0009055967,0.0002260867,0.0001413214,0.0002673209,0.00007895512],"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":[0.0001837218,0.0001844484,0.06357259,0.00004654007,0.0001869664,0.0002663812,0.000185295,0.7828473,0.00169458,0.002137205,0.002250109,0.1464449],"study_design_scores_gemma":[0.000001217053,0.00001085644,0.002107359,0.000002911873,0.000008538286,0.00001012073,0.00001253993,0.9968594,0.000192999,0.0006824196,0.0001082236,0.000003442775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6942962,0.0006927349,0.3001507,0.0005693099,0.00005681647,0.00004696896,0.0006395225,0.001112371,0.002435426],"genre_scores_gemma":[0.9802075,0.0001342177,0.01825005,0.00005672312,0.00003513474,0.00001935791,0.0005862737,0.00002246306,0.0006882729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01033839,"threshold_uncertainty_score":0.02055645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01874915355862433,"score_gpt":0.224503800019179,"score_spread":0.2057546464605547,"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."}}