{"id":"W4406972075","doi":"10.1080/10920277.2024.2442416","title":"A Nested GLM Framework with Neural Network Encoding and Spatially Constrained Clustering in Non-Life Insurance Ratemaking","year":2025,"lang":"en","type":"article","venue":"North American Actuarial Journal","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Artificial neural network; Generalized linear model; Econometrics; Computer science; Mathematics; Artificial intelligence; Machine learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009676549,0.0002910194,0.0005824309,0.0003458389,0.001018461,0.0005595004,0.0004145303,0.00008213768,0.00002317951],"category_scores_gemma":[0.0004500177,0.000269663,0.00009668317,0.002087476,0.001032095,0.0004093862,0.000106161,0.0008583312,0.000001474387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001469856,"about_ca_system_score_gemma":0.0005755498,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004139636,"about_ca_topic_score_gemma":0.05449461,"domain_scores_codex":[0.9970059,0.0005063279,0.0006509946,0.000398557,0.0005833085,0.0008549037],"domain_scores_gemma":[0.9983239,0.0004360717,0.0006157163,0.0002057769,0.0001445774,0.0002740179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004355524,0.0000400887,0.9245116,0.00002893518,0.0001087512,0.0001595021,0.004051658,0.02068468,0.000004630716,0.0004150163,0.00005057345,0.04950907],"study_design_scores_gemma":[0.001315218,0.0001537229,0.9904086,0.0004557307,0.00005164202,0.00001462692,0.003029237,0.00305236,6.78857e-7,0.0002435599,0.0009083317,0.0003663088],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9688637,0.000106184,0.02442187,0.001025732,0.001314257,0.0005558704,0.00000459961,0.00006495965,0.003642792],"genre_scores_gemma":[0.9922014,0.0004247973,0.004789345,0.001458699,0.001067799,0.00001972633,0.000002057752,0.00002096413,0.00001518725],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06589705,"threshold_uncertainty_score":0.9999756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01140030191625178,"score_gpt":0.2864571913487837,"score_spread":0.2750568894325319,"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."}}