Calibrating the Heston model with deep differential networks

TL;DR

This paper introduces a deep differential network that efficiently calibrates the Heston model by learning option prices and their sensitivities, improving accuracy and speed over traditional methods.

Contribution

The novel deep differential network framework enables fast, accurate calibration of the Heston model by directly learning pricing formulas and derivatives.

Findings

Outperforms non-differential neural networks in calibration accuracy

Reduces computational time compared to global optimizers

Effective on real equity market data

Abstract

We propose a gradient-based deep learning framework to calibrate the Heston option pricing model (Heston, 1993). Our neural network, henceforth deep differential network (DDN), learns both the Heston pricing formula for plain-vanilla options and the partial derivatives with respect to the model parameters. The price sensitivities estimated by the DDN are not subject to the numerical issues that can be encountered in computing the gradient of the Heston pricing function. Thus, our network is an excellent pricing engine for fast gradient-based calibrations. Extensive tests on selected equity markets show that the DDN significantly outperforms non-differential feedforward neural networks in terms of calibration accuracy. In addition, it dramatically reduces the computational time with respect to global optimizers that do not use gradient information.