{"id":"W3173285506","doi":"10.3390/risks9070126","title":"Improving Explainability of Major Risk Factors in Artificial Neural Networks for Auto Insurance Rate Regulation","year":2021,"lang":"en","type":"article","venue":"Risks","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Transparency (behavior); Artificial neural network; Variable (mathematics); Computer science; Work (physics); Actuarial science; Insurance industry; Econometrics; Machine learning; Risk analysis (engineering); Artificial intelligence; Economics; Business; Engineering; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003386169,0.0009156146,0.0008354982,0.0007346211,0.0003906905,0.001036625,0.0008300518,0.0009756851,0.001149356],"category_scores_gemma":[0.01025296,0.0004218843,0.0009877312,0.000614611,0.0004604004,0.001129189,0.001079266,0.001678183,0.0001349132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009412142,"about_ca_system_score_gemma":0.001029765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007993861,"about_ca_topic_score_gemma":0.005878396,"domain_scores_codex":[0.9990121,0.0004800409,0.00006695252,0.0001639338,0.0001799982,0.00009698005],"domain_scores_gemma":[0.9937347,0.004893096,0.0005631629,0.0002289467,0.0004908857,0.00008927083],"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":[0.00009424218,0.00008523,0.005305885,0.00004979669,0.0000774725,0.0001045002,0.0001031747,0.9629353,0.001374723,0.005126748,0.0002061379,0.02453682],"study_design_scores_gemma":[0.000001699945,0.00001018955,0.0005187629,0.000004265754,0.000006703489,0.00000434232,0.000005409013,0.9977857,0.0001584762,0.001451331,0.00005003066,0.000003148965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3011331,0.0006962933,0.6950133,0.0006890944,0.00004755266,0.00006014471,0.00009624745,0.0003601621,0.001904099],"genre_scores_gemma":[0.964357,0.0002740872,0.03419536,0.00006755301,0.00003498757,0.00006042877,0.0001438028,0.0000402499,0.0008265452],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007993861,"threshold_uncertainty_score":0.01790798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03912109199705017,"score_gpt":0.316868814324062,"score_spread":0.2777477223270118,"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."}}