{"id":"W4410977227","doi":"10.2139/ssrn.5279418","title":"Hedging targeted risks with reinforcement learning: application to life insurance contracts with embedded guarantees","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Reinforcement learning; Actuarial science; Reinforcement; Life insurance; Business; Risk analysis (engineering); Computer science; Artificial intelligence; Engineering","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":[0.003579836,0.0007265907,0.001232693,0.0004645743,0.0003858956,0.001163768,0.001171203,0.002152685,0.003162968],"category_scores_gemma":[0.014246,0.0003816352,0.0005573186,0.0006397881,0.001171615,0.001206848,0.001420557,0.002197995,0.000168053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001239454,"about_ca_system_score_gemma":0.001246375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01213869,"about_ca_topic_score_gemma":0.005800895,"domain_scores_codex":[0.9994051,0.0003637019,0.00002199475,0.00007629125,0.00007388403,0.000058941],"domain_scores_gemma":[0.9902399,0.008590131,0.0003201976,0.0002266608,0.0003400772,0.0002831631],"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":[0.0001112721,0.0001611357,0.001500061,0.00004545328,0.00002365748,0.00007975633,0.00006179111,0.9692069,0.0002796846,0.01063808,0.0004148686,0.01747736],"study_design_scores_gemma":[0.00001457977,0.00001356273,0.00008194709,0.000002147215,0.000002723259,0.000003586994,0.000004143131,0.9961047,0.00003962721,0.003686487,0.00004406252,0.00000237067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3285656,0.001126108,0.661662,0.001299173,0.0001198548,0.000140629,0.0001225424,0.0005302877,0.006433783],"genre_scores_gemma":[0.9650095,0.0002043521,0.03241497,0.00006776343,0.00003924248,0.00005551648,0.00003226364,0.00003105926,0.00214544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01213869,"threshold_uncertainty_score":0.02413607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01304525296057735,"score_gpt":0.2999370847352468,"score_spread":0.2868918317746695,"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."}}