Deep Learning Enhanced Realized GARCH

TL;DR

This paper introduces a novel deep learning-enhanced realized GARCH model that combines LSTM networks with realized volatility measures, improving volatility forecasting and risk assessment in financial markets.

Contribution

It develops a new framework integrating deep learning with econometric models, offering superior predictive accuracy and adaptability to stylized facts in volatility.

Findings

Outperforms benchmark models in volatility prediction

Provides accurate tail risk and option pricing forecasts

Demonstrates robustness across diverse stock indices during COVID-19

Abstract

We propose a new approach to volatility modeling by combining deep learning (LSTM) and realized volatility measures. This LSTM-enhanced realized GARCH framework incorporates and distills modeling advances from financial econometrics, high frequency trading data and deep learning. Bayesian inference via the Sequential Monte Carlo method is employed for statistical inference and forecasting. The new framework can jointly model the returns and realized volatility measures, has an excellent in-sample fit and superior predictive performance compared to several benchmark models, while being able to adapt well to the stylized facts in volatility. The performance of the new framework is tested using a wide range of metrics, from marginal likelihood, volatility forecasting, to tail risk forecasting and option pricing. We report on a comprehensive empirical study using 31 widely traded stock indices over a time period that includes COVID-19 pandemic.