What type of study is this?

This is a Quantitative Study study.

October 8, 2025Open Access

Time Deep Gradient Flow Method for pricing American options

Key Points

Both TDGF and DGM methods show superior accuracy for pricing american options compared to traditional Monte Carlo methods.
Time deep gradient flow method achieves faster training times when pricing options under the black-scholes and heston models.
Sample strategies during training are crucial for enhancing performance in multidimensional option pricing.
The research extends methods up to five dimensions, showcasing the versatility of neural networks in financial modeling.

Abstract

In this research, we explore neural network-based methods for pricing multidimensional American put options under the BlackScholes and Heston model, extending up to five dimensions. We focus on two approaches: the Time Deep Gradient Flow (TDGF) method and the Deep Galerkin Method (DGM). We extend the TDGF method to handle the free-boundary partial differential equation inherent in American options. We carefully design the sampling strategy during training to enhance performance. Both TDGF and DGM achieve high accuracy while outperforming conventional Monte Carlo methods in terms of computational speed. In particular, TDGF tends to be faster during training than DGM.

Read Full Paperexternally

Perguntar à IA

Bookmark

View Full Paper

Cite This Study

Jasper Rou (Wed,) studied this question.

synapsesocial.com/papers/68e6a0f4718ef0a556b33d49 https://doi.org/https://doi.org/10.48550/arxiv.2507.17606

Perguntar à IA

Bookmark

View Full Paper