{"id":"W4367189531","doi":"10.48550/arxiv.2304.13128","title":"Computing Volatility Surfaces using Generative Adversarial Networks with Minimal Arbitrage Violations","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Volatility (finance); Computer science; Discriminator; Artificial neural network; Generative grammar; Generative adversarial network; Arbitrage; Adversarial system; Regularization (linguistics); Local volatility; Artificial intelligence; Implied volatility; Deep learning; Econometrics; Mathematics; Economics; Financial economics; Telecommunications","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":[0.001173456,0.00101994,0.001132778,0.0007021714,0.0003643361,0.001200816,0.001115609,0.00129035,0.002101176],"category_scores_gemma":[0.003866156,0.0006074764,0.0008485714,0.0004524513,0.001053755,0.001635496,0.00165724,0.002136743,0.000400758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009402305,"about_ca_system_score_gemma":0.0007286983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002319251,"about_ca_topic_score_gemma":0.002595653,"domain_scores_codex":[0.9995567,0.0001540739,0.00002044001,0.00008658958,0.000125035,0.00005709011],"domain_scores_gemma":[0.9986132,0.0009622321,0.0001203115,0.0001102793,0.0001145159,0.00007936825],"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":[0.00003424399,0.00001294344,0.0004689765,0.00001597979,0.00002016332,0.00004166204,0.00001568707,0.9753867,0.0008210614,0.009820898,0.0004801767,0.01288145],"study_design_scores_gemma":[0.00000124403,0.000003096531,0.00002393415,0.000001158511,8.645032e-7,0.000003967184,0.000001044319,0.9956534,0.0001274965,0.004138078,0.00004409408,0.000001524154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03529967,0.0002256874,0.9614646,0.0003033074,0.00003456327,0.00002910739,0.0000788506,0.000733048,0.001831048],"genre_scores_gemma":[0.8873454,0.0002369833,0.1083588,0.0002923837,0.00006602835,0.00009567325,0.000369009,0.0002452383,0.002990498],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002319251,"threshold_uncertainty_score":0.007029176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3420209961778948,"score_gpt":0.318928224227056,"score_spread":0.02309277195083875,"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."}}