Paper: arXiv 2511.08606
Authors: Qi Feng, Guang Lin, Purav Matlia, Denny Serdarevic
Abstract
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 (BSDE) from a single pair of stock and option trajectories. Unlike existing approaches to identifying stochastic differential equations-which typically require ergodicity-our framework leverages the risk-neutral measure, thereby eliminating the ergodicity assumption and enabling BSDE recovery from limited financial time series data. Using this algorithm, we are able not only to make forward-looking predictions but also to generate new synthetic data paths consistent with the underlying probabilistic law.
Complexity vs Empirical Score
- Math Complexity: 9.0/10
- Empirical Rigor: 7.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper involves advanced stochastic calculus (Feynman-Kac, BSDEs, risk-neutral measures) and complex numerical methods (DNN-based PDE solving, stochastic SINDy, SR3), indicating high mathematical density. Empirical rigor is strong, with a detailed algorithmic workflow for both prediction and data generation using real-world financial data, though the lack of complete backtesting metrics keeps it from a perfect 10.
Research Flowchart
flowchart TD A["Research Goal:<br>Discover BSDE underlying<br>Feynman-Kac formula"] --> B["Data Input:<br>Single pair of Stock<br>& Option trajectories"] B --> C["Core Methodology:<br>Data-driven Risk-Neutral<br>Stochastic SINDy"] C --> D["Computational Process:<br>Recover BSDE from<br>Limited Financial Data"] D --> E["Key Finding 1:<br>Forward Prediction<br>of derivative values"] D --> F["Key Finding 2:<br>Generation of synthetic<br>probabilistic law paths"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper introduces a stochastic SINDy algorithm under the risk‑neutral measure to discover backward stochastic differential equations from a single stock‑option trajectory.
Source sentence
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.
Assumes 5
- Data are generated under the risk‑neutral probability measure. model
Source sentence
our framework leverages the risk-neutral measure, thereby eliminating the ergodicity assumption and enabling BSDE recovery from limited financial time series data.
- Ergodicity of the underlying process is not required. statistical
Source sentence
Unlike existing approaches to identifying stochastic differential equations—which typically require ergodicity—our framework leverages the risk-neutral measure, thereby eliminating the ergodicity assumption
- The drift coefficient r is fixed under the risk‑neutral measure. model
Source sentence
The drift coefficient r is assumed to be a fixed, and corresponds to the risk-neutral probability measure Q.
- Only a single pair of discrete stock and option trajectories is available. data
Source sentence
The dataset consists of a single pair of discrete trajectories Du = {(Xti, Yti)}i=N i=0 with terminal value XtN = XT ; YtN = YT .
Show 1 more
- Diffusion coefficient σ(x) can be estimated from quadratic variation of the stock price. model
Source sentence
= √(Δ⟨Xti⟩/Δti) which is often noisy due to the discrete sampling of the trajectory.
Data
- Black‑Scholes synthetic data synthetic unknown
Source sentence
= … The numerical results for the Black‑Scholes model are presented in Figure [1-(a)(b)(c)(d)].
- Apple market data (AAPL) options public
Source sentence
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.
Costs
Not applicable
Finds 3
- The stochastic SINDy algorithm successfully recovers a sparse BSDE representation for the Black‑Scholes model. theoretical
Source sentence
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 )
- The method yields accurate forward‑looking option price predictions on real Apple data. predictive-accuracy
Source sentence
We present the prediction in Figure [1-(e)] and generate stock‑option pairs in Figure [1-(f)(g)].
- Synthetic stock‑option paths generated by the discovered BSDE match the statistical properties of the original data. performance
Source sentence
generate new synthetic data paths consistent with the underlying probabilistic law.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 27 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.