Forecasting Stock Market Realized Variance with Echo State Neural Networks

Milan Ficura

European Financial and Accounting Journal, 2017, vol. 2017, issue 3, 145-155

Abstract: Echo State Neural Networks (ESN) were applied to forecast the realized variance time series of 19 major stock market indices. Symmetric ESN and asymmetric AESN models were constructed and compared with the benchmark realized variance models HAR and AHAR that approximate the long memory of the realized variance process with a heterogeneous auto-regression. The results show that asymmetric models generally outperform symmetric ones, indicating that a correlation between volatility and returns plays an important role for volatility forecasting. Additionally, models utilizing a logarithmic transformation of the time series achieved generally better results than models applied directly to the realized variance. Echo State Neural Networks outperformed HAR and AHAR models for several important indices (S&P500, DJIA and Nikkei indices), but on average they achieved slightly worse results than the AHAR model. Nevertheless, the results show that Echo State Neural Networks represent an easy-to-use and accurate tool for realized variance forecasting, whose performance may potentially be further improved with meta-parameter optimization.

Keywords: Realized variance; HAR model; Echo State Neural Networks (search for similar items in EconPapers)
JEL-codes: C45 C53 C58 (search for similar items in EconPapers)
Date: 2017
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://efaj.vse.cz/doi/10.18267/j.efaj.193.html (text/html)
http://efaj.vse.cz/doi/10.18267/j.efaj.193.pdf (application/pdf)
free of charge

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:prg:jnlefa:v:2017:y:2017:i:3:id:193:p:145-156

Ordering information: This journal article can be ordered from
European Financial and Accounting Journal, University of Economics, Prague, nám. W. Churchilla 4, 130 67 Prague 3, Czech Republic
http://efaj.vse.cz

DOI: 10.18267/j.efaj.193

Access Statistics for this article

European Financial and Accounting Journal is currently edited by Efaj Journal

More articles in European Financial and Accounting Journal from Prague University of Economics and Business Contact information at EDIRC.
Bibliographic data for series maintained by Stanislav Vojir ().