Should you use GARCH models for forecasting volatility? A comparison to GRU neural networks

Article


Pallotta, A. and Ciciretti, V. 2023. Should you use GARCH models for forecasting volatility? A comparison to GRU neural networks. Studies in Nonlinear Dynamics & Econometrics. https://doi.org/10.1515/snde-2022-0025
TypeArticle
TitleShould you use GARCH models for forecasting volatility? A comparison to GRU neural networks
AuthorsPallotta, A. and Ciciretti, V.
Abstract

The GARCH model is the most used technique for forecasting conditional volatility. However, the nearly integrated behaviour of the conditional variance originates from structural changes which are not accounted for by standard GARCH models. We compare the forecasting performance of the GARCH model to three regime switching models: namely, the Markov Switching GARCH, the Hidden Markov Model, and the Gated Recurrent Unit neural network. We define the number of optimal states by means of three methods: piecewise linear regression, Baum–Welch algorithm and Markov Chain Monte Carlo. Since forecasting volatility models face the bias-variance trade-off, we compare their out-of-sample forecasting performance via a walk-forward methodology. Moreover, we provide a robustness check for the results by applying k-fold cross-validation to the original time series. The Gated Recurrent Unit network is the best suited for volatility forecasting, while the Hidden Markov Model is the best at discerning the market regimes.

Keywordsvolatility forecasting; GARCH; Hidden Markov Models; Markow switching GARCH; Gated Recurrent Unit; walk-forward
Sustainable Development Goals9 Industry, innovation and infrastructure
Middlesex University ThemeCreativity, Culture & Enterprise
LanguageEnglish
PublisherDe Gruyter
JournalStudies in Nonlinear Dynamics & Econometrics
ISSN
Electronic1558-3708
Publication dates
Online04 Dec 2023
Publication process dates
Accepted03 Oct 2023
Deposited13 Feb 2024
Output statusPublished
Accepted author manuscript
File Access Level
Restricted
Copyright Statement

The final publication is available at www.degruyter.com

Digital Object Identifier (DOI)https://doi.org/10.1515/snde-2022-0025
Permalink -

https://repository.mdx.ac.uk/item/x71q3

Restricted files

Accepted author manuscript

  • 26
    total views
  • 6
    total downloads
  • 4
    views this month
  • 0
    downloads this month

Export as