{"id":"W4389675160","doi":"10.3390/math11244943","title":"Deep Reinforcement Learning for Dynamic Stock Option Hedging: A Review","year":2023,"lang":"en","type":"review","venue":"Mathematics","topic":"Stochastic processes and financial applications","field":"Economics, Econometrics and Finance","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Stochastic volatility; Computer science; Econometrics; CVAR; Volatility (finance); Mathematical optimization; Mathematics; Artificial intelligence; Economics; Financial economics; Expected shortfall; Portfolio","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":[0.0009294173,0.0008899358,0.001020499,0.001006998,0.0001465182,0.0009232602,0.0009404281,0.001012103,0.003675979],"category_scores_gemma":[0.002305566,0.0004112727,0.0007150181,0.001685787,0.0003226225,0.001171214,0.0006310504,0.001150433,0.001238318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005141363,"about_ca_system_score_gemma":0.001051658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001968072,"about_ca_topic_score_gemma":0.001835238,"domain_scores_codex":[0.9998129,0.00003581988,0.00002666112,0.00004967211,0.00006079446,0.00001415354],"domain_scores_gemma":[0.9990807,0.0006735881,0.00006637094,0.00002455198,0.0001254479,0.0000294689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004711296,0.00009706296,0.000443741,0.008987284,0.0001404703,0.00005306786,0.00003284773,0.009551664,0.0003830238,0.009388914,0.00950347,0.9613712],"study_design_scores_gemma":[0.00008288644,0.0006061742,0.003362571,0.01437175,0.0008056163,0.000966362,0.0001405245,0.03347609,0.002377042,0.02799436,0.9156854,0.0001312522],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0008695009,0.989164,0.006620803,0.0005256158,0.0001804356,0.00001486386,0.00004912713,0.0000465164,0.002529193],"genre_scores_gemma":[0.01152719,0.9825869,0.004012006,0.0002341045,0.0002526736,0.00002435431,0.00009232115,0.00001405596,0.00125634],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.003675979,"threshold_uncertainty_score":0.01229733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1170095940338367,"score_gpt":0.3362618703945343,"score_spread":0.2192522763606976,"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."}}