{"id":"W4415127930","doi":"10.3390/risks13100198","title":"Application of Standard Machine Learning Models for Medicare Fraud Detection with Imbalanced Data","year":2025,"lang":"en","type":"article","venue":"Risks","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Columbia College","funders":"","keywords":"Interpretability; Random forest; AdaBoost; Decision tree; Feature selection; Resampling; Preprocessor; Feature (linguistics); Ensemble learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004031396,0.00008675153,0.0001520995,0.0001057136,0.00009940589,0.00003407883,0.001035652,0.00006252272,9.004885e-7],"category_scores_gemma":[0.00008791656,0.00007495523,0.00001694056,0.0003731819,0.0000420749,0.0004514536,0.0002306061,0.0001308153,7.595351e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004849828,"about_ca_system_score_gemma":0.00007706361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009179469,"about_ca_topic_score_gemma":0.0000498485,"domain_scores_codex":[0.9990296,0.0000374425,0.0002072095,0.000395889,0.0002058465,0.0001239718],"domain_scores_gemma":[0.9983293,0.00009284671,0.0001848058,0.001181809,0.0001853237,0.00002593275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001311755,0.00004548682,0.001646673,0.0001402963,0.00004695249,3.003461e-7,0.0001790795,0.001747342,0.01530015,0.04252338,0.0008548074,0.9373844],"study_design_scores_gemma":[0.0003760008,0.00009648426,0.0006120653,0.00003739777,0.00001276552,8.278001e-7,0.0000191049,0.9214734,0.05769778,0.007931235,0.01165706,0.00008582502],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003045254,0.0001218665,0.9980122,0.0002861858,0.00004025432,0.0004275274,0.0001555075,0.0003060489,0.0003458097],"genre_scores_gemma":[0.8056896,0.00004988403,0.1938146,0.00004585806,0.00001253517,0.0001200213,0.0002240219,0.000006430689,0.00003702423],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9372985,"threshold_uncertainty_score":0.3056586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04827192005258184,"score_gpt":0.3258992892147127,"score_spread":0.2776273691621309,"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."}}