{"paper_id":"2511.08606","title":"Data-driven Feynman-Kac Discovery with Applications to Prediction and Data Generation","authors":["Qi Feng","Guang Lin","Purav Matlia","Denny Serdarevic"],"paper_date":"2025-11-05","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2511.08606v1","page_url":"https://thequant.space/flowcharts/data-driven-feynman-kac-discovery-with-applications-to-predi/","scores":{"empirical_rigor":7,"math_complexity":9,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper introduces a stochastic SINDy algorithm under the risk‑neutral measure to discover backward stochastic differential equations from a single stock‑option trajectory.","quote":"Specifically, we introduce the first stochastic SINDy method formulated under the risk-neutral probability measure to recover the backward stochastic differential equation (BSDE) from a single pair of stock and option trajectories.","summary":"In this paper, we propose a novel data-driven framework for discovering probabilistic laws underlying the Feynman-Kac formula. Specifically, we introduce the first stochastic SINDy method formulated under the risk-neutral probability measure to recover the backward stochastic differential equation…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Data are generated under the risk‑neutral probability measure.","type":"model","stated":"explicit","quote":"our framework leverages the risk-neutral measure, thereby eliminating the ergodicity assumption and enabling BSDE recovery from limited financial time series data."},{"assumption":"Ergodicity of the underlying process is not required.","type":"statistical","stated":"explicit","quote":"Unlike existing approaches to identifying stochastic differential equations—which typically require ergodicity—our framework leverages the risk-neutral measure, thereby eliminating the ergodicity assumption"},{"assumption":"The drift coefficient r is fixed under the risk‑neutral measure.","type":"model","stated":"explicit","quote":"The drift coefficient r is assumed to be a fixed, and corresponds to the risk-neutral probability measure Q."},{"assumption":"Only a single pair of discrete stock and option trajectories is available.","type":"data","stated":"explicit","quote":"The dataset consists of a single pair of discrete trajectories Du = {(Xti, Yti)}i=N i=0 with terminal value XtN = XT ; YtN = YT ."},{"assumption":"Diffusion coefficient σ(x) can be estimated from quadratic variation of the stock price.","type":"model","stated":"explicit","quote":"= √(Δ⟨Xti⟩/Δti) which is often noisy due to the discrete sampling of the trajectory."}]},"datasets":{"status":"available","items":[{"name":"Black‑Scholes synthetic data","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"= … The numerical results for the Black‑Scholes model are presented in Figure [1-(a)(b)(c)(d)]."},{"name":"Apple market data (AAPL)","provider":"public market data","kind":"options","access":"public","period":"11/14/2024 to 07/18/2025","universe":"single ticker AAPL","quote":"Example 2: Market data Apple. Data was collected from the ticker AAPL from 11/14/2024 up to expiration 07/18/2025 with timer intervals of 1 second at a strike price at K = 170."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"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 stochastic SINDy algorithm successfully recovers a sparse BSDE representation for the Black‑Scholes model.","kind":"theoretical","quote":"our stochastic SINDy discovers the BSDE dYt = −[1.018(ut)(dt) + 0.106(St)(us)(dt) + 0.016(S2 t )(uss)(dt)] + 0.2(St)(us)(dBQ t )"},{"finding":"The method yields accurate forward‑looking option price predictions on real Apple data.","kind":"predictive-accuracy","quote":"We present the prediction in Figure [1-(e)] and generate stock‑option pairs in Figure [1-(f)(g)]."},{"finding":"Synthetic stock‑option paths generated by the discovered BSDE match the statistical properties of the original data.","kind":"performance","quote":"generate new synthetic data paths consistent with the underlying probabilistic law."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":27,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"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":"2026-11-14T17:22:39Z"},"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/"}