{"id":"W4381562444","doi":"10.48550/arxiv.2306.10582","title":"Machine Learning and Hamilton-Jacobi-Bellman Equation for Optimal Decumulation: a Comparison Study","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hamilton–Jacobi–Bellman equation; Mathematical optimization; Stochastic control; Optimal control; Bellman equation; Computer science; Viscosity solution; Artificial neural network; Partial differential equation; Mathematics; Applied mathematics; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00285584,0.0005882964,0.001146444,0.0004727882,0.0004205945,0.001106853,0.001177079,0.001501424,0.002622876],"category_scores_gemma":[0.0091443,0.0002900021,0.0006234043,0.0006428233,0.001067564,0.001689948,0.001015885,0.001670985,0.000219785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001628653,"about_ca_system_score_gemma":0.001642514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007995729,"about_ca_topic_score_gemma":0.004131821,"domain_scores_codex":[0.9994585,0.0002596069,0.00002684327,0.00007507823,0.0001288211,0.0000512614],"domain_scores_gemma":[0.9964346,0.00263736,0.0002510213,0.0001582725,0.0004055339,0.0001133002],"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":[0.00002529522,0.00002527446,0.0006660071,0.00006543392,0.00002251665,0.00002751336,0.00002425365,0.9286158,0.0001596229,0.06104741,0.0005661686,0.008754616],"study_design_scores_gemma":[0.000003114662,0.000007401283,0.00008478111,0.000005166274,0.000001885135,0.000003481788,0.000002200561,0.9916996,0.00003793071,0.00799961,0.0001524947,0.00000245341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1194366,0.006324097,0.8500205,0.004354871,0.0002790466,0.00007469415,0.0001953875,0.0001664688,0.01914829],"genre_scores_gemma":[0.9242485,0.002406432,0.06684663,0.0003241635,0.0002332988,0.0001208489,0.0001731832,0.00006919878,0.005577807],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007995729,"threshold_uncertainty_score":0.01589835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2053389822718643,"score_gpt":0.2987020907294419,"score_spread":0.09336310845757764,"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."}}