{"id":"W4321497586","doi":"10.3389/frai.2023.1129370","title":"Gamma and vega hedging using deep distributional reinforcement learning","year":2023,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"University of Sussex; University of Toronto; Royal Bank of Canada; Rotman School of Management, University of Toronto; Global Risk Institute in Financial Services; TD Bank","keywords":"Transaction cost; Vega; Portfolio; Reinforcement learning; Robustness (evolution); Quantile regression; Computer science; Econometrics; Asset (computer security); Database transaction; Position (finance); Economics; Microeconomics; Artificial intelligence; Financial economics; Finance","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001760914,0.0006555689,0.0008512517,0.0003823327,0.0002395971,0.0008718491,0.00098265,0.0009865655,0.002244595],"category_scores_gemma":[0.00490534,0.0003494897,0.0004191584,0.0002908244,0.000776966,0.0009783477,0.0008614632,0.001341842,0.0001970888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007889103,"about_ca_system_score_gemma":0.0006929946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003625411,"about_ca_topic_score_gemma":0.003339317,"domain_scores_codex":[0.9997211,0.0001116989,0.00001432699,0.00005306866,0.00004951583,0.0000503968],"domain_scores_gemma":[0.9981517,0.001325242,0.0001635693,0.0001024868,0.0001582807,0.00009869301],"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":[0.00005088772,0.00004470711,0.001052462,0.00002057507,0.00002840979,0.00005576873,0.00003837812,0.9623045,0.0007465041,0.01125562,0.000317041,0.02408536],"study_design_scores_gemma":[0.000002971121,0.00001043528,0.00004593557,0.000001932497,0.000002031988,0.000003399582,0.000001460854,0.9968929,0.0001058357,0.0028893,0.00004216406,0.000001688738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1595049,0.0005725942,0.834911,0.0005546252,0.00005921206,0.00004315014,0.00005038536,0.0004225084,0.003881687],"genre_scores_gemma":[0.959272,0.0001216374,0.03794813,0.0001079676,0.00002322855,0.00004214001,0.00003915195,0.00002879462,0.002416994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003625411,"threshold_uncertainty_score":0.009312749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1957249365602509,"score_gpt":0.4214700578682315,"score_spread":0.2257451213079806,"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."}}