{"id":"W4406911682","doi":"10.3390/math13030434","title":"Bi-Partitioned Feature-Weighted K-Means Clustering for Detecting Insurance Fraud Claim Patterns","year":2025,"lang":"en","type":"article","venue":"Mathematics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Feature (linguistics); Insurance fraud; k-means clustering; Computer science; Pattern recognition (psychology); Data mining; Artificial intelligence; Business; Actuarial science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001409908,0.001075307,0.001055305,0.005158706,0.001198565,0.001441889,0.001478795,0.001264424,0.0006667109],"category_scores_gemma":[0.004716784,0.0003685816,0.001203681,0.004443696,0.0006667341,0.001433171,0.001270897,0.001088246,0.0008322952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008876934,"about_ca_system_score_gemma":0.00140679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006827601,"about_ca_topic_score_gemma":0.006553887,"domain_scores_codex":[0.9985108,0.0003185091,0.0001308802,0.0003417574,0.0005613321,0.0001366141],"domain_scores_gemma":[0.9987797,0.000289225,0.0002059635,0.0001926572,0.0004802708,0.00005215869],"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":[0.0005646427,0.000344124,0.01147056,0.0004091565,0.0004296175,0.0003108062,0.0006801294,0.2092263,0.02878825,0.01318187,0.008572899,0.7260217],"study_design_scores_gemma":[0.00001828429,0.00005580125,0.00346639,0.00003833116,0.00005351283,0.0001918857,0.0001890079,0.9741032,0.00715522,0.01117144,0.003510796,0.00004616796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04284107,0.0008020196,0.9536877,0.0002592891,0.00008128511,0.000124581,0.0002078213,0.0008482106,0.001148038],"genre_scores_gemma":[0.3964119,0.000592372,0.5998463,0.0001322981,0.00008067341,0.0002086593,0.001065103,0.0001416732,0.001521136],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006827601,"threshold_uncertainty_score":0.01357573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0228842605894272,"score_gpt":0.2819166096203233,"score_spread":0.2590323490308961,"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."}}