{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008070491,0.0009353956,0.0007794303,0.001121682,0.0004186953,0.001074172,0.0009244701,0.0007399727,0.0004578204],"category_scores_gemma":[0.01959619,0.0002892678,0.0007204778,0.0008918717,0.0004265594,0.001618191,0.0007942818,0.001127754,0.0002266698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005938253,"about_ca_system_score_gemma":0.0009284074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002870438,"about_ca_topic_score_gemma":0.00315872,"domain_scores_codex":[0.9980544,0.001050828,0.0001508519,0.000226475,0.0004075812,0.0001098669],"domain_scores_gemma":[0.9857861,0.01045307,0.0007046889,0.00109119,0.001767413,0.0001974734],"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":[0.002277207,0.001158729,0.04519125,0.0005293071,0.0004461313,0.000137101,0.0004739893,0.4706588,0.01033564,0.003713404,0.003346629,0.4617318],"study_design_scores_gemma":[0.00002718514,0.0002942005,0.003232035,0.00003706375,0.00005822895,0.00003564373,0.00007080609,0.9902275,0.00445106,0.0008235663,0.0007300642,0.00001264364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7462097,0.005846614,0.24019,0.0009947426,0.00032846,0.0003204774,0.0005360155,0.001827421,0.003746557],"genre_scores_gemma":[0.9051326,0.0009233344,0.09246275,0.0001214163,0.00009493579,0.0001303062,0.0006570792,0.00005638928,0.0004211577],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008070491,"threshold_uncertainty_score":0.04268134,"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."}}