{"id":"W4406230441","doi":"10.3390/jrfm18010023","title":"Credit Card Default Prediction: An Empirical Analysis on Predictive Performance Using Statistical and Machine Learning Methods","year":2025,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Machine learning; Artificial intelligence; Random forest; Support vector machine; Confusion matrix; Computer science; Linear discriminant analysis; Artificial neural network; Logistic regression; Credit card; Metric (unit); Receiver operating characteristic; Python (programming language); Engineering","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":[0.0009750011,0.0001994814,0.0004261995,0.0008270876,0.000477702,0.000192046,0.0001172057,0.00009689653,0.00001527645],"category_scores_gemma":[0.0002185617,0.0001687407,0.0001053779,0.0008479289,0.00009083914,0.0006397221,0.0001400511,0.0004167855,9.796227e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005713967,"about_ca_system_score_gemma":0.0000226775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001980038,"about_ca_topic_score_gemma":0.00003897767,"domain_scores_codex":[0.9986109,0.00007411608,0.0005173819,0.0002899263,0.0002907804,0.0002169],"domain_scores_gemma":[0.9992108,0.00007498684,0.0003761729,0.0001222394,0.0001817572,0.0000340925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009252771,0.0001988704,0.5285998,0.0002248336,0.0003030449,0.00004189605,0.0001416053,0.01386525,0.000008955079,0.005969263,0.0005131346,0.4492081],"study_design_scores_gemma":[0.0007357773,0.0002053275,0.7467262,0.0001042609,0.002069261,0.000003239964,0.0001806426,0.2228364,0.000004326695,0.001347149,0.02565793,0.0001294576],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4806668,0.0003589632,0.5171215,0.00004803837,0.0005407142,0.0001300481,0.00003607484,0.0000299627,0.001067914],"genre_scores_gemma":[0.9917923,0.0008731217,0.00623731,0.0002127652,0.0007952174,0.000005289936,0.00002729398,0.00001140015,0.00004530564],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5111255,"threshold_uncertainty_score":0.6881047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01729484740383092,"score_gpt":0.2939771887913403,"score_spread":0.2766823413875094,"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."}}