Applying Deep Learning to Calibrate Stochastic Volatility Models

TL;DR

This paper applies Differential Machine Learning to efficiently calibrate stochastic volatility models, specifically the Heston model, using neural networks trained on option pricing data, significantly reducing calibration time and improving accuracy.

Contribution

The work demonstrates the effectiveness of DML in calibrating the Heston model, introducing regularisation techniques, and comparing DML with classical DL methods for improved performance.

Findings

DML outperforms classical DL in calibration accuracy.

Regularisation techniques reduce overfitting and enhance generalisation.

Neural networks trained with DML significantly decrease calibration time.

Abstract

Stochastic volatility models, where the volatility is a stochastic process, can capture most of the essential stylized facts of implied volatility surfaces and give more realistic dynamics of the volatility smile/skew. However, they come with the significant issue that they take too long to calibrate. Alternative calibration methods based on Deep Learning (DL) techniques have been recently used to build fast and accurate solutions to the calibration problem. Huge and Savine developed a Differential Machine Learning (DML) approach, where Machine Learning models are trained on samples of not only features and labels but also differentials of labels to features. The present work aims to apply the DML technique to price vanilla European options (i.e. the calibration instruments), more specifically, puts when the underlying asset follows a Heston model and then calibrate the model on the trained network. DML allows for fast training and accurate pricing. The trained neural network dramatically reduces Heston calibration's computation time. In this work, we also introduce different regularisation techniques, and we apply them notably in the case of the DML. We compare their performance in reducing overfitting and improving the generalisation error. The DML performance is also compared to the classical DL (without differentiation) one in the case of Feed-Forward Neural Networks. We show that the DML outperforms the DL. The complete code for our experiments is provided in the GitHub repository: https://github.com/asridi/DML-Calibration-Heston-Model