Forecasting Financial Returns Volatility: A GARCH-SVR Model

Hao Sun () and Bo Yu ()
Additional contact information
Hao Sun: Dalian University of Technology
Bo Yu: Dalian University of Technology

Computational Economics, 2020, vol. 55, issue 2, No 3, 471 pages

Abstract: Abstract Support vector regression (SVR) is a semiparametric estimation method that has been used extensively in the forecasting of financial time series volatility. In this paper, we seek to design a two-stage forecasting volatility method by combining SVR and the GARCH model (GARCH-SVR) instead of replacing the maximum likelihood estimation with the SVR estimation method to estimate the GARCH parameters (SVR-GARCH). To investigate the effect of innovations in different distributions, we propose the GARCH-SVR and GARCH-t-SVR models based on the standardized normal distribution and the standardized Student’s t distribution, respectively. To allow asymmetric volatility effects, we also consider the GJR-(t)-SVR models. The forecast performance of the GARCH-(t)-SVR and GJR-(t)-SVR models is evaluated using the daily closing price of the S&P 500 index and the daily exchange rate of the British pound against the US dollar. The empirical results obtained for one-period-ahead forecasts suggest that the GARCH-(t)-SVR models and GJR-(t)-SVR models improve the volatility forecasting ability.

Keywords: Volatility forecasting; Support vector regression; GARCH; GJR (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (8)

Downloads: (external link)
http://link.springer.com/10.1007/s10614-019-09896-w Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:kap:compec:v:55:y:2020:i:2:d:10.1007_s10614-019-09896-w

Ordering information: This journal article can be ordered from
http://www.springer. ... ry/journal/10614/PS2

DOI: 10.1007/s10614-019-09896-w

Access Statistics for this article

Computational Economics is currently edited by Hans Amman

More articles in Computational Economics from Springer, Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().