{"id":"W4388585148","doi":"10.18280/ijsse.130509","title":"Detection of Health Insurance Fraud using Bayesian Optimized XGBoost","year":2023,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Bayesian probability; Environmental health; Computer science; Health insurance; Actuarial science; Computer security; Business; Risk analysis (engineering); Medicine; Artificial intelligence; Economics; Health care","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":[0.003649101,0.001218906,0.002428428,0.002168673,0.0007659406,0.001460058,0.001920904,0.002025877,0.001485102],"category_scores_gemma":[0.003733479,0.0004947126,0.001196731,0.001563143,0.0007680802,0.0008319534,0.0009335454,0.001576255,0.0006603625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00108207,"about_ca_system_score_gemma":0.002312852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009279938,"about_ca_topic_score_gemma":0.00634399,"domain_scores_codex":[0.9986485,0.0004902083,0.00008427261,0.0002186822,0.0003188341,0.0002395354],"domain_scores_gemma":[0.9988016,0.0006105111,0.0001910496,0.00007682976,0.0002200237,0.00009988766],"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":[0.0007818865,0.0007395188,0.01729849,0.0002652227,0.0002814574,0.0002568355,0.0001183094,0.7246094,0.002109365,0.004143292,0.008358668,0.2410375],"study_design_scores_gemma":[0.00001748986,0.00004949302,0.0007326778,0.00002646078,0.00001115873,0.00002616724,0.0000169112,0.9971463,0.0003210929,0.001168423,0.0004779778,0.000005897574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.320363,0.006298918,0.659051,0.002352968,0.0005833899,0.0005240557,0.0006723684,0.00376222,0.006392064],"genre_scores_gemma":[0.8445448,0.0009477083,0.1485033,0.0009450138,0.0001806316,0.0002460212,0.001172397,0.0001072984,0.003352983],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009279938,"threshold_uncertainty_score":0.01929849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01430264312689245,"score_gpt":0.2661878477067442,"score_spread":0.2518852045798518,"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."}}