{"id":"W2976895931","doi":"10.48550/arxiv.1909.11532","title":"Deep Neural Network Framework Based on Backward Stochastic Differential Equations for Pricing and Hedging American Options in High Dimensions","year":2019,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Stochastic processes and financial applications","field":"Economics, Econometrics and Finance","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Curse of dimensionality; Artificial neural network; Computer science; Dimension (graph theory); Stochastic differential equation; Residual; Quadratic equation; Mathematical optimization; Function (biology); Applied mathematics; State space; State (computer science); Valuation of options; Algorithm; Mathematics; Artificial intelligence; Econometrics; Pure mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008325229,0.0003617113,0.0009341513,0.0008589408,0.0003436411,0.0001863103,0.0004751085,0.0003449961,0.00002459198],"category_scores_gemma":[0.001283549,0.0004605315,0.000171837,0.0004545903,0.0002717277,0.00007804665,0.0004843066,0.001452281,0.00001788051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006619183,"about_ca_system_score_gemma":0.0001777799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002919756,"about_ca_topic_score_gemma":0.0003151461,"domain_scores_codex":[0.9966577,0.00003617463,0.001018202,0.001286003,0.00007933779,0.0009225768],"domain_scores_gemma":[0.9957457,0.002638096,0.0004997232,0.0008698298,0.00007616892,0.0001704878],"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":[0.00006887296,0.0001393267,0.001999114,0.00007667967,0.00002399548,8.158252e-7,0.0001269896,0.7642676,0.0000012412,0.2225301,0.000003359001,0.01076199],"study_design_scores_gemma":[0.000545508,0.0001340665,0.0194718,0.0002099664,0.00000877264,5.129185e-7,0.00009816513,0.8361226,3.397783e-7,0.1428825,0.0001302608,0.0003955569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.110403,0.0003777178,0.8838372,0.0009242165,0.0007632575,0.00240546,0.0003801483,0.00004357375,0.0008654417],"genre_scores_gemma":[0.9849542,0.000422661,0.01224184,0.0001629079,0.0003609293,0.001558889,0.0001679543,0.00008501289,0.00004559559],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8745512,"threshold_uncertainty_score":0.9997846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03542190823135259,"score_gpt":0.2934158842296873,"score_spread":0.2579939759983347,"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."}}