{"id":"W4402891761","doi":"10.1109/access.2024.3468993","title":"Machine Learning Based Method for Insurance Fraud Detection on Class Imbalance Datasets With Missing Values","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ontario Ministry of Research and Innovation; National Natural Science Foundation of China; Prince Sattam bin Abdulaziz University","keywords":"Computer science; Class (philosophy); Machine learning; Artificial intelligence; Data mining","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0006719337,0.0002127371,0.0001969844,0.0002308623,0.0002583078,0.0009705404,0.001245388,0.00008216547,0.000003935813],"category_scores_gemma":[0.0001235582,0.0001768679,0.0000481589,0.0007104289,0.0000413806,0.001631014,0.00007867559,0.0003353858,0.00001304816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009821678,"about_ca_system_score_gemma":0.00008449962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004563398,"about_ca_topic_score_gemma":0.0000146496,"domain_scores_codex":[0.9982268,0.000160864,0.0002426933,0.0007579066,0.0003213932,0.0002903687],"domain_scores_gemma":[0.998331,0.000588313,0.0001390352,0.0007853419,0.00008824337,0.00006803693],"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":[0.0002210006,0.0001510822,0.001663584,0.0005999336,0.00007446689,0.00004860177,0.000146652,0.01093443,0.06617495,0.004350821,0.006264796,0.9093697],"study_design_scores_gemma":[0.0002014489,0.0001374999,0.001046833,0.0001792175,0.000007327816,0.00000886759,0.000001362769,0.673705,0.2989995,0.001223395,0.02428379,0.0002056896],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000654514,0.0001478838,0.9958207,0.000930567,0.0004504683,0.0003674883,0.0002593592,0.001211958,0.00015708],"genre_scores_gemma":[0.7696292,0.0000186923,0.2291642,0.0006319123,0.0001156475,0.0001831315,0.0001634217,0.00003442484,0.0000593474],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.909164,"threshold_uncertainty_score":0.9358943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03522758099449765,"score_gpt":0.3528297738485358,"score_spread":0.3176021928540382,"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."}}