{"id":"W4392757155","doi":"10.1080/10920277.2023.2279782","title":"A Flexible Hierarchical Insurance Claims Model with Gradient Boosting and Copulas","year":2024,"lang":"en","type":"article","venue":"North American Actuarial Journal","topic":"Insurance and Financial Risk Management","field":"Economics, Econometrics and Finance","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Copula (linguistics); Boosting (machine learning); Gradient boosting; Econometrics; Computer science; Economics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.002944046,0.0008407483,0.001564144,0.000943567,0.0006030211,0.001288386,0.002787966,0.001690595,0.003966508],"category_scores_gemma":[0.004730778,0.0007740706,0.001318709,0.001182779,0.001061568,0.001337665,0.001202039,0.001700978,0.0008097038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001209831,"about_ca_system_score_gemma":0.0014274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01561334,"about_ca_topic_score_gemma":0.01044592,"domain_scores_codex":[0.9991574,0.0003453221,0.00003595508,0.0001824362,0.0001441965,0.0001345716],"domain_scores_gemma":[0.9983959,0.0009006705,0.0002356263,0.0001220524,0.0002096363,0.0001361908],"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":[0.00006304499,0.0000486859,0.00182038,0.00003695135,0.00003655403,0.0001265281,0.00005818849,0.9533003,0.0004613612,0.03033926,0.001778223,0.01193058],"study_design_scores_gemma":[0.000005058625,0.000006114799,0.0001612252,0.000002837599,0.000003984265,0.000007483882,0.000001965816,0.9961132,0.00002868447,0.003533338,0.0001331181,0.000003035012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09480724,0.0006317017,0.8986537,0.0008734458,0.00008840987,0.0001145932,0.000874677,0.0006154641,0.003340736],"genre_scores_gemma":[0.8527038,0.0004941821,0.1355848,0.0003578541,0.0001468621,0.0002463606,0.001104965,0.0001699475,0.009191103],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01561334,"threshold_uncertainty_score":0.03104496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01965093821642587,"score_gpt":0.2227416359532634,"score_spread":0.2030906977368375,"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."}}