{"id":"W4416187194","doi":"10.28924/2291-8639-23-2025-296","title":"Comparative Analysis of Data Augmentation Methods for Enhancing the Performance of Churn Prediction Models","year":2025,"lang":"","type":"article","venue":"International Journal of Analysis and Applications","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Northern Border University","keywords":"Oversampling; Random forest; Boosting (machine learning); Naive Bayes classifier; Support vector machine; Predictive modelling; Gradient boosting; Decision tree","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":[0.002016765,0.0001571091,0.0006939567,0.002410607,0.0001990258,0.0001817711,0.0008188065,0.00005778726,0.00005881304],"category_scores_gemma":[0.00004684225,0.0001252437,0.0004436016,0.003598936,0.0001368565,0.001577659,0.0002054967,0.0001250615,3.924217e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006364852,"about_ca_system_score_gemma":0.00008738292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001488118,"about_ca_topic_score_gemma":0.0002229516,"domain_scores_codex":[0.9975067,0.00006244624,0.001626851,0.0002677663,0.0004285366,0.0001077177],"domain_scores_gemma":[0.9942057,0.000488381,0.002570825,0.0003560822,0.002362944,0.00001611415],"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":[0.001119622,0.001499572,0.05713358,0.0006684451,0.1659899,3.100998e-7,0.002662221,0.382417,0.0364965,0.04343905,0.0008186895,0.3077551],"study_design_scores_gemma":[0.0006440231,0.00002625737,0.02818106,0.00009049858,0.03899187,4.879935e-7,0.002250183,0.9237945,0.002678006,0.001007008,0.002243212,0.00009291239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1053905,0.001030003,0.8916515,0.0007208101,0.0001666479,0.0003673272,0.000211268,0.000003413946,0.0004586119],"genre_scores_gemma":[0.9899729,0.001167136,0.007713299,0.0001314018,0.0002353426,0.0000332572,0.0006356533,0.000004756473,0.0001062429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8845825,"threshold_uncertainty_score":0.510729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06130317914360049,"score_gpt":0.4132942130868781,"score_spread":0.3519910339432776,"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."}}