A neural network enhanced volatility component model

Volatility prediction, a central issue in financial econometrics, attracts increasing attention in the data science literature as advances in computational methods enable us to develop models with great forecasting precision. In this paper, we draw upon both strands of the literature and develop a n...

Full description

Bibliographic Details
Main Authors: Zhai, Jia, Cao, Yi, Liu, Xiaoquan
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://eprints.nottingham.ac.uk/60139/
_version_ 1848799733499297792
author Zhai, Jia
Cao, Yi
Liu, Xiaoquan
author_facet Zhai, Jia
Cao, Yi
Liu, Xiaoquan
author_sort Zhai, Jia
building Nottingham Research Data Repository
collection Online Access
description Volatility prediction, a central issue in financial econometrics, attracts increasing attention in the data science literature as advances in computational methods enable us to develop models with great forecasting precision. In this paper, we draw upon both strands of the literature and develop a novel two-component volatility model. The realized volatility is decomposed by a nonparametric filter into long- and short-run components, which are modeled by an artificial neural network and an ARMA process, respectively. We use intraday data on four major exchange rates and a Chinese stock index to construct daily realized volatility and perform out-of-sample evaluation of volatility forecasts generated by our model and well-established alternatives. Empirical results show that our model outperforms alternative models across all statistical metrics and over different forecasting horizons. Furthermore, volatility forecasts from our model offer economic gain to a mean-variance utility investor with higher portfolio returns and Sharpe ratio.
first_indexed 2025-11-14T20:40:21Z
format Article
id nottingham-60139
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:40:21Z
publishDate 2020
recordtype eprints
repository_type Digital Repository
spelling nottingham-601392020-03-23T01:22:58Z https://eprints.nottingham.ac.uk/60139/ A neural network enhanced volatility component model Zhai, Jia Cao, Yi Liu, Xiaoquan Volatility prediction, a central issue in financial econometrics, attracts increasing attention in the data science literature as advances in computational methods enable us to develop models with great forecasting precision. In this paper, we draw upon both strands of the literature and develop a novel two-component volatility model. The realized volatility is decomposed by a nonparametric filter into long- and short-run components, which are modeled by an artificial neural network and an ARMA process, respectively. We use intraday data on four major exchange rates and a Chinese stock index to construct daily realized volatility and perform out-of-sample evaluation of volatility forecasts generated by our model and well-established alternatives. Empirical results show that our model outperforms alternative models across all statistical metrics and over different forecasting horizons. Furthermore, volatility forecasts from our model offer economic gain to a mean-variance utility investor with higher portfolio returns and Sharpe ratio. 2020-02-19 Article PeerReviewed application/pdf en https://eprints.nottingham.ac.uk/60139/1/Xiaoquan-merged.pdf Zhai, Jia, Cao, Yi and Liu, Xiaoquan (2020) A neural network enhanced volatility component model. Quantitative Finance . pp. 1-15. ISSN 1469-7688 Wavelet analysis; ARMA process; Volatility prediction; Exchange rates http://dx.doi.org/10.1080/14697688.2019.1711148 doi:10.1080/14697688.2019.1711148 doi:10.1080/14697688.2019.1711148
spellingShingle Wavelet analysis; ARMA process; Volatility prediction; Exchange rates
Zhai, Jia
Cao, Yi
Liu, Xiaoquan
A neural network enhanced volatility component model
title A neural network enhanced volatility component model
title_full A neural network enhanced volatility component model
title_fullStr A neural network enhanced volatility component model
title_full_unstemmed A neural network enhanced volatility component model
title_short A neural network enhanced volatility component model
title_sort neural network enhanced volatility component model
topic Wavelet analysis; ARMA process; Volatility prediction; Exchange rates
url https://eprints.nottingham.ac.uk/60139/
https://eprints.nottingham.ac.uk/60139/
https://eprints.nottingham.ac.uk/60139/