{"id":"W7132886114","doi":"","title":"Hedging Financial Options with Deep Reinforcement Learning","year":2024,"lang":"","type":"dissertation","venue":"TSpace","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Dalhousie University","keywords":"Reinforcement learning; Stochastic volatility; Hedge; Volatility (finance); Implied volatility; SABR volatility model; Volatility smile","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007241187,0.001014318,0.00114615,0.00148194,0.001522417,0.00147482,0.001252322,0.0006297592,0.004779837],"category_scores_gemma":[0.01493049,0.0008416482,0.0004920106,0.003850607,0.0002383597,0.0003877643,0.000348116,0.002497941,0.00202418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004108227,"about_ca_system_score_gemma":0.001516049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002439855,"about_ca_topic_score_gemma":0.0003932188,"domain_scores_codex":[0.9909053,0.000969337,0.001538593,0.00204478,0.003357198,0.001184795],"domain_scores_gemma":[0.992698,0.003467667,0.00125657,0.001122357,0.00103623,0.0004191929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001532954,0.00009427137,0.0008066497,0.0006103009,0.0002962703,0.0003067857,0.1267822,0.4182356,0.000755291,0.005934843,0.003408386,0.4412365],"study_design_scores_gemma":[0.001756461,0.002449957,0.007105056,0.006618301,0.00145615,0.0002405484,0.1400171,0.7095469,0.001633678,0.006204737,0.1191909,0.003780269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2164767,0.004458127,0.5445395,0.0007188014,0.009591702,0.001897427,0.000002484469,0.0005256369,0.2217897],"genre_scores_gemma":[0.4867461,0.0002495929,0.0454818,0.0001015851,0.0008905494,0.0002498176,0.0001494359,0.0002248928,0.4659062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4990577,"threshold_uncertainty_score":0.9998034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06385080045175527,"score_gpt":0.4260753090577681,"score_spread":0.3622245086060129,"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."}}