Recurrent Conditional Heteroskedasticity

TL;DR

The paper introduces RECH models that integrate recurrent neural networks into traditional volatility models, enhancing their ability to analyze and forecast financial volatility more accurately.

Contribution

It presents a novel class of models combining neural networks with GARCH-type models, capturing complex volatility dynamics overlooked by existing models.

Findings

RECH models outperform traditional models in out-of-sample forecasts.

They effectively capture stylized facts of financial volatility.

Models reveal new effects in volatility dynamics.

Abstract

We propose a new class of financial volatility models, called the REcurrent Conditional Heteroskedastic (RECH) models, to improve both in-sample analysis and out-ofsample forecasting of the traditional conditional heteroskedastic models. In particular, we incorporate auxiliary deterministic processes, governed by recurrent neural networks, into the conditional variance of the traditional conditional heteroskedastic models, e.g. GARCH-type models, to flexibly capture the dynamics of the underlying volatility. RECH models can detect interesting effects in financial volatility overlooked by the existing conditional heteroskedastic models such as the GARCH, GJR and EGARCH. The new models often have good out-of-sample forecasts while still explaining well the stylized facts of financial volatility by retaining the well-established features of econometric GARCH-type models. These properties are illustrated through simulation studies and applications to thirty-one stock indices and exchange rate data. . An user-friendly software package together with the examples reported in the paper are available at https://github.com/vbayeslab.