{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008309867,0.0003831435,0.0006425881,0.001539495,0.0002866151,0.0006602549,0.00009112534,0.0002084164,0.00009567077],"category_scores_gemma":[0.00006940825,0.0004072683,0.0001073009,0.001858542,0.00004619726,0.0007357507,0.000152766,0.0004792268,0.00001731871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009936282,"about_ca_system_score_gemma":0.00001706648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001950973,"about_ca_topic_score_gemma":0.000007181439,"domain_scores_codex":[0.9978755,0.00001979611,0.0007607033,0.0005504133,0.0002382744,0.0005553396],"domain_scores_gemma":[0.9994457,0.0001312545,0.0001433051,0.0001490373,0.00008485536,0.00004579392],"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":[0.00001651747,0.00009979831,0.004507657,0.004152691,0.0002713082,0.000004156503,0.0005538172,0.9826819,0.0006598223,0.005756707,0.00001169255,0.001283929],"study_design_scores_gemma":[0.0006002431,0.00001085,0.0001908683,0.001196944,0.0009114536,0.000002994374,0.0004254791,0.9921252,0.00002913614,0.003327733,0.0008387255,0.0003403899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3537516,0.001455715,0.6416379,0.00008578035,0.0001225915,0.0003489861,0.000001112613,0.0001137473,0.002482633],"genre_scores_gemma":[0.9929397,0.0003637591,0.00523734,0.00003473489,0.00009609424,0.00003530655,0.00001608134,0.0000414768,0.001235573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6391881,"threshold_uncertainty_score":0.9998379,"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."}}