Work

Deep learning enhanced volatility modeling with covariates

Year: 2024

Type: article

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.

Source: Finance research letters

DOI: 10.1016/j.frl.2024.106145

Authors: Hien Thi Nguyen, Hoang Nguyen, Minh-Ngoc Tran

Institutions: Linköping University, Thuongmai University, The University of Sydney

Language: English

Topic: Financial Risk and Volatility Modeling

Subfield: Finance

Field: Economics, Econometrics and Finance

Domain: Social Sciences

Open Access status: hybrid

Estimated APC paid: $3,350

OpenAlex ID: W4402883721

FWCI: 1.43

Cites: 60

Cited by: 4

Related to: 10