{"paper_id":"2406.00459","title":"Machine Learning Methods for Pricing Financial Derivatives","authors":["Lei Fan","Justin Sirignano"],"paper_date":"2024-06-01","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2406.00459v1","page_url":"https://thequant.space/flowcharts/machine-learning-methods-for-pricing-financial-derivatives/","scores":{"empirical_rigor":8,"math_complexity":9,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a fast stochastic gradient descent algorithm for training neural network SDE models for European options and a PDE optimization approach for American options.","quote":"For European options, we develop a fast stochastic gradient descent (SGD) algorithm for training the neural network-SDE model. Our SGD algorithm uses two independent SDE paths to obtain an unbiased estimate of the direction of steepest descent. For American options, we optimize over the corresponding Kolmogorov partial","summary":"Stochastic differential equation (SDE) models are the foundation for pricing and hedging financial derivatives. The drift and volatility functions in SDE models are typically chosen to be algebraic functions with a small number (less than 5) parameters which can be calibrated to market data. A more…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Drift and volatility functions are modeled by neural networks with many degrees of freedom.","type":"model","stated":"explicit","quote":"A more flexible approach is to use neural networks to model the drift and volatility functions, which provides more degrees-of-freedom to match observed market data."},{"assumption":"Two independent SDE paths provide an unbiased gradient estimate.","type":"statistical","stated":"explicit","quote":"Our SGD algorithm uses two independent SDE paths to obtain an unbiased estimate of the direction of steepest descent."},{"assumption":"Monte‑Carlo paths are i.i.d. and the risk‑free rate r is constant.","type":"model","stated":"explicit","quote":"where (Sℓ t, Y ℓ t ) are i.i.d. Monte Carlo paths of the SDE (St, Yt) and (without loss of generality) we have set Ti = T for notational convenience."},{"assumption":"Training and testing splits are random with 80%/20% allocation each day.","type":"data","stated":"explicit","quote":"On each day, there are approximately 1100 contract pairs (call and put options). For each day, we randomly split the contracts into training and testing sets (80% training and 20% test)."},{"assumption":"Automatic differentiation and GPUs provide fast parallel optimization over many PDEs.","type":"execution","stated":"explicit","quote":"We will use automatic differentiation (AD) and GPUs for fast, parallelized optimization over the PDEs for large numbers of contracts."}]},"datasets":{"status":"available","items":[{"name":"S&P 500 index options (American)","provider":null,"kind":"options","access":"unknown","period":null,"universe":"100 stocks from the S&P 500","quote":"The first dataset consists of American options on 100 different stocks from the S&P 500."},{"name":"S&P 100 index options (European and American)","provider":null,"kind":"options","access":"unknown","period":null,"universe":"S&P 100 index","quote":"The second dataset consists of European and American options on the S&P 100 Index."},{"name":"Two‑month recalibration dataset","provider":null,"kind":"options","access":"unknown","period":"September–October 2017 (42 trading days)","universe":"approximately 1100 contract pairs per day","quote":"The dataset consists of a 2 month time period (September and October of 2017), which includes 42 trading days. On each day, there are approximately 1100 contract pairs (call and put options)."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"pricing-calibration","findings":[{"finding":"The recalibrated neural network‑SDE model outperforms the non‑recalibrated model on out‑of‑sample test data.","kind":"performance","quote":"The recalibrated method outperforms the model with no recalibration, indicating that there is a benefit to recalibrating the neural network-SDE model."},{"finding":"Neural network SDE models achieve better pricing performance than traditional SDE models such as Black‑Scholes, Dupire local volatility, and Heston.","kind":"pricing-calibration","quote":"The neural-network-based SDE models are compared against the Black-Scholes model, the Dupire's local volatility model, and the Heston model."},{"finding":"For American options, the 2D‑NN neural network model shows superior performance over traditional SDE models.","kind":"performance","quote":"The neural network models, especially the 2D‑NN model, have better performance than the traditional SDE models."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":40,"citations":{"cited_by_in_corpus":5,"by_independent_authors":5,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":3,"unclassified":1},"independent_papers":[{"paper":{"paper_id":"2603.12375","title":"Feynman-Kac Derivatives Pricing on the Full Forward Curve","paper_date":"2026-03-12","authors":["Kevin Mott"],"empirical_rigor":6.5,"page_url":"https://thequant.space/flowcharts/feynman-kac-derivatives-pricing-on-the-full-forward-curve/"},"how":"uses_method_or_data","quote":null}],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T18:08:37Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}