{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003225264,0.0001615607,0.0002161163,0.0001638854,0.0002229396,0.0002107592,0.0008218724,0.0001035331,0.000004414297],"category_scores_gemma":[0.0001782183,0.0001559067,0.00006960611,0.0004297142,0.00002517463,0.0003408054,0.0002159171,0.0001451732,0.00001402857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007547418,"about_ca_system_score_gemma":0.00003653905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000292023,"about_ca_topic_score_gemma":0.00001685057,"domain_scores_codex":[0.9988503,0.00002837687,0.0003419558,0.000333694,0.0001733638,0.0002722782],"domain_scores_gemma":[0.9984877,0.0002658225,0.000188357,0.000882597,0.0001362168,0.00003936377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004653591,0.001123111,0.006538827,0.005991715,0.0002974785,0.00001829907,0.009945759,0.0003212798,0.05471446,0.6935774,0.03099917,0.1964259],"study_design_scores_gemma":[0.0006342601,0.00006441421,0.002532862,0.0006672535,0.00001918385,0.00001222971,0.0001632029,0.7886003,0.1126926,0.08614495,0.008017372,0.0004513525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004888543,0.00002506884,0.9914597,0.001118094,0.0002465547,0.0004918188,0.00004406831,0.000722696,0.001003453],"genre_scores_gemma":[0.3320262,0.00001021548,0.666881,0.0003560712,0.0000352011,0.000215682,0.00001580269,0.00001467991,0.000445161],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.788279,"threshold_uncertainty_score":0.6357692,"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."}}