Deep Calibration With Artificial Neural Network: A Performance Comparison on Option Pricing Models

TL;DR

This paper demonstrates that artificial neural networks can efficiently calibrate complex option pricing models, outperforming traditional Monte Carlo methods in accuracy and speed, with applications to GARCH-type models.

Contribution

The study introduces a neural network-based calibration method for GARCH-type option models, reducing computational complexity and improving performance over Monte Carlo simulations.

Findings

ANN calibration outperforms MCS in accuracy

ANN approach offers faster computation times

Greeks of options are effectively estimated

Abstract

This paper explores Artificial Neural Network (ANN) as a model-free solution for a calibration algorithm of option pricing models. We construct ANNs to calibrate parameters for two well-known GARCH-type option pricing models: Duan's GARCH and the classical tempered stable GARCH that significantly improve upon the limitation of the Black-Scholes model but have suffered from computation complexity. To mitigate this technical difficulty, we train ANNs with a dataset generated by Monte Carlo Simulation (MCS) method and apply them to calibrate optimal parameters. The performance results indicate that the ANN approach consistently outperforms MCS and takes advantage of faster computation times once trained. The Greeks of options are also discussed.