Improving forecasts of GARCH family models with the artificial neural networks: An application to the daily returns in Istanbul Stock Exchange

Bildirici M. E., Ersin O. O.

EXPERT SYSTEMS WITH APPLICATIONS, vol.36, no.4, pp.7355-7362, 2009 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 36 Issue: 4
  • Publication Date: 2009
  • Doi Number: 10.1016/j.eswa.2008.09.051
  • Journal Name: EXPERT SYSTEMS WITH APPLICATIONS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.7355-7362
  • Keywords: Volatility, Stock returns, ARCH/GARCH, EGARCH, TGARCH, PGARCH, APGARCH, Artificial neural networks, AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTICITY, S-AND-P, VOLATILITY, PERCEPTRON, VARIANCE
  • Yıldız Technical University Affiliated: Yes

Abstract

In the study, we discussed the ARCH/GARCH family models and enhanced them with artificial neural networks to evaluate the volatility of daily returns for 23.10.1987-22.02.2008 period in Istanbul Stock Exchange. We proposed ANN-APGARCH model to increase the forecasting performance of APGARCH model. The ANN-extended versions of the obtained GARCH models improved forecast results. It is noteworthy that daily returns in the ISE show strong volatility clustering, asymmetry and nonlinearity characteristics. (C) 2008 Elsevier Ltd. All rights reserved.