Deep learning enhanced volatility modeling with covariates

Hien Thi Nguyen, Hoang Nguyen and Minh-Ngoc Tran

Finance Research Letters, 2024, vol. 69, issue PB

Abstract: Exogenous information such as policy news and economic indicators can have the potential to trigger significant movements in financial asset volatility. This article presents a model, called the RECH-X model, that allows incorporating exogenous variables into a recurrent neural network for volatility modeling and forecasting. The RECH-X model can allow for abrupt changes in the volatility level and effectively capture the complex serial dependence structure in the volatility dynamics. We demonstrate in a wide range of applications that the RECH-X model consistently outperforms the benchmark models in terms of volatility modeling and forecasting.

Keywords: GARCH; GARCH-X; Volatility forecast; Realized measures; Sequence Monte Carlo (search for similar items in EconPapers)
JEL-codes: C10 C53 C58 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1544612324011747
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:finlet:v:69:y:2024:i:pb:s1544612324011747

DOI: 10.1016/j.frl.2024.106145

Access Statistics for this article

Finance Research Letters is currently edited by R. Gençay

More articles in Finance Research Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().