Pricing Derivatives by Path Integral and Neural Networks

TL;DR

This paper introduces two innovative algorithms for pricing financial derivatives: one based on path integrals and another utilizing neural networks, both validated against standard methods for accuracy.

Contribution

It presents a novel combination of path integral techniques and neural network models for derivative pricing, enhancing computational efficiency and accuracy.

Findings

Both methods achieve high accuracy compared to standard procedures.

Neural network approach offers faster computation.

Path integral method provides a new perspective on option pricing.

Abstract

Recent progress in the development of efficient computational algorithms to price financial derivatives is summarized. A first algorithm is based on a path integral approach to option pricing, while a second algorithm makes use of a neural network parameterization of option prices. The accuracy of the two methods is established from comparisons with the results of the standard procedures used in quantitative finance.