Physics Informed Neural Network for Option Pricing

Ashish Dhiman, Yibei Hu
12/10/2023
q-fin.PRcs.CEcs.LG

No official code found. Best implementation: ashish1610dhiman/pinn_option_pricing (35 stars, MIT, last commit 2024-01-11).

Abstract

We apply a physics-informed deep-learning approach the PINN approach to the Black-Scholes equation for pricing American and European options. We test our approach on both simulated as well as real market data, compare it to analytical/numerical benchmarks. Our model is able to accurately capture the price behaviour on simulation data, while also exhibiting reasonable performance for market data. We also experiment with the architecture and learning process of our PINN model to provide more understanding of convergence and stability issues that impact performance.

View on arXivView PDF

Code Implementations(1)

ashish1610dhiman/pinn_option_pricingCommunity100%
MIT

Scientific Machine Learning for Option Pricing

3516Python, Jupyter NotebookOct 18, 20232 years agoMIT
option-pricingphysics-informed-neural-networks

Similar Papers

Option Pricing on Noisy Intermediate-Scale Quantum Computers: A Quantum Neural Network Approach

84% match2026

Deep Learning for Options Trading: An End-To-End Approach

83% match2024

The AI Black-Scholes: Finance-Informed Neural Network

83% match2024

Error Analysis of Deep PDE Solvers for Option Pricing

83% match2025

Deep Learning vs. Black-Scholes: Option Pricing Performance on Brazilian Petrobras Stocks

83% match2025

Residual Learning in Empirical Asset Pricing

82% match1 repo2026

Cite this paper

@article{dhiman2023physics,
  title  = {Physics Informed Neural Network for Option Pricing},
  author = {Ashish Dhiman and Yibei Hu},
  year   = {2023},
  eprint = {2312.06711},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2312.06711v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2312.06711.svg)](https://codeofpaper.com/paper/2312.06711)

Discussion