{"id":"W2971556193","doi":"10.1017/asb.2019.25","title":"A CLASS OF MIXTURE OF EXPERTS MODELS FOR GENERAL INSURANCE: APPLICATION TO CORRELATED CLAIM FREQUENCIES","year":2019,"lang":"en","type":"article","venue":"Astin Bulletin","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Identifiability; Computer science; Inference; Class (philosophy); Expectation–maximization algorithm; Data mining; Econometrics; Logit; Multivariate statistics; Data set; Logistic regression; Set (abstract data type); Artificial intelligence; Machine learning; Mathematics; Statistics; Maximum likelihood","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":[0.01113239,0.0009689434,0.00174555,0.001935629,0.0005451275,0.001651667,0.002856904,0.002439033,0.003714883],"category_scores_gemma":[0.03316038,0.0008589305,0.001949761,0.001822772,0.001830887,0.002229311,0.001866444,0.002561467,0.0004602416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00110824,"about_ca_system_score_gemma":0.0009505398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006417574,"about_ca_topic_score_gemma":0.004747587,"domain_scores_codex":[0.9961601,0.002421043,0.0001319554,0.0005619883,0.0004995994,0.0002253136],"domain_scores_gemma":[0.9825371,0.01417792,0.001344208,0.001021011,0.0006810934,0.0002386646],"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":[0.0000957747,0.00006411492,0.002774915,0.00007582835,0.0001126876,0.0002293203,0.0002041337,0.7844297,0.0005177432,0.182422,0.0007252335,0.02834865],"study_design_scores_gemma":[0.000007360189,0.00001369666,0.0003129901,0.000009599358,0.000009743992,0.00003858682,0.00001751091,0.9660364,0.00009479595,0.0331195,0.0003259186,0.0000139373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03297602,0.0001325105,0.9652923,0.000250057,0.00001439556,0.00005679202,0.00008879128,0.0001435498,0.001045483],"genre_scores_gemma":[0.7269275,0.0004964521,0.2664056,0.0001780594,0.00009987009,0.0003361944,0.0003930826,0.0001008947,0.005062365],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01113239,"threshold_uncertainty_score":0.05887443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03148779184123828,"score_gpt":0.317522757976733,"score_spread":0.2860349661354947,"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."}}