{"id":"W4403230631","doi":"10.1515/apjri-2024-0002","title":"Gaussian Mixture Regression Model with Sparsity for Clustering of Territory Risk in Auto Insurance","year":2024,"lang":"en","type":"article","venue":"Asia-Pacific Journal of Risk and Insurance","topic":"Insurance and Financial Risk Management","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"","keywords":"Cluster analysis; Mixture model; Regression; Computer science; Econometrics; Logistic regression; Regression analysis; Statistics; Mathematics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001100542,0.0002359708,0.0006875677,0.000462697,0.0001286827,0.00006885417,0.000232874,0.0001762421,0.000004104894],"category_scores_gemma":[0.00008581085,0.0001974291,0.0001716323,0.0003381675,0.0001142983,0.0006150235,0.00003783542,0.0006412825,0.000003636158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007889148,"about_ca_system_score_gemma":0.0000503862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001395372,"about_ca_topic_score_gemma":0.0001177774,"domain_scores_codex":[0.9982387,0.00003275739,0.0009560403,0.0003603935,0.0001031759,0.0003089511],"domain_scores_gemma":[0.9985921,0.00008635151,0.0009229918,0.0002446373,0.00007524822,0.00007863353],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009002537,0.000163835,0.9099149,0.0005186033,0.0001135733,0.00006214468,0.003657473,0.008736988,0.00005868715,0.007440696,0.0008045241,0.06762834],"study_design_scores_gemma":[0.002610244,0.0005834836,0.8844572,0.001868915,0.00003999648,0.00006817753,0.0007435882,0.06141451,0.0002121847,0.02576029,0.02167548,0.0005658874],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.898174,0.02375864,0.07327519,0.000240001,0.0007934124,0.0003121793,0.000764361,0.00001852483,0.002663674],"genre_scores_gemma":[0.9771824,0.01728082,0.005167955,0.00001436971,0.0001515289,0.00001019956,0.000003067074,0.00003048181,0.0001591233],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07900844,"threshold_uncertainty_score":0.8050924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01333080440173405,"score_gpt":0.2142398018763244,"score_spread":0.2009089974745903,"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."}}