{"id":"W4402095110","doi":"10.23977/jeis.2024.090307","title":"Research on medical insurance fraud identification method based on multi-source datasets","year":2024,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Identification (biology); Medical insurance; Insurance fraud; Computer science; Business; Data science; Data mining; Actuarial science","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01292582,0.00008712833,0.0001119171,0.001323815,0.0002920552,0.001106331,0.001525654,0.00006529001,0.000007688516],"category_scores_gemma":[0.001246688,0.0000666559,0.00003043819,0.002196794,0.0001905851,0.007834822,0.0001170733,0.0007141203,0.00003721866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000224047,"about_ca_system_score_gemma":0.001192813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002150897,"about_ca_topic_score_gemma":5.577195e-7,"domain_scores_codex":[0.9965674,0.0001358794,0.0005832539,0.0002112711,0.002208817,0.0002934253],"domain_scores_gemma":[0.9980604,0.0004346161,0.0002608394,0.0004848565,0.0005966924,0.0001625825],"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":[0.00003038823,0.00009908291,0.00003545368,0.00005071911,0.000005672003,0.000005085276,0.0004718849,0.001416578,0.003923499,0.4111643,0.007655824,0.5751415],"study_design_scores_gemma":[0.0001682165,0.0002978645,0.002355344,0.000123861,0.000001162306,0.000045123,0.00002484598,0.853802,0.0155707,0.0007303029,0.1268007,0.00007995057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001810688,0.0001417771,0.9935681,0.003666017,0.000209578,0.0001036384,0.00001712393,0.00005237359,0.0004307228],"genre_scores_gemma":[0.9484698,0.0005564194,0.04955573,0.001326831,0.0000447713,0.000008499499,0.00001524633,0.000004518013,0.00001813736],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9466591,"threshold_uncertainty_score":0.9999306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04516819087620674,"score_gpt":0.4145474269694186,"score_spread":0.3693792360932119,"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."}}