Publication detail

Baruník J.: How Does Neural Networks Enhance the Predictability of Central European Stock Returns?

Author(s): doc. PhDr. Jozef Baruník Ph.D.,
Type: Articles in journals with impact factor
Year: 2008
Number: 7
ISSN / ISBN: 0015-1920
Published in: Finance a úvěr-Czech Journal of Economics and Finance, 7-8 (58), pp.359-376 PDF
Publishing place: Prague
Keywords: emerging stock markets, predictability of stock returns, neural networks, optimization algorithms
JEL codes: C45, C53, E44
Suggested Citation: Baruník J. (2008): How Does Neural Networks Enhance the Predictability of Central European Stock Returns? Czech Journal of Economics and Finance, 7-8 (58):359-376
Grants: GAUK 46108: New Nonlinear Capital Markets Theories: Fractal, Bifurcational and Behavioral Approach IES Research Framework Institutional task (2005-2011) Integration of the Czech economy into European union and its development
Abstract: In this paper, we apply neural networks as nonparametric and nonlinear methods to Central European (Czech, Polish, Hungarian, and German) stock market returns modeling. In the first part, we present the intuition of neural networks and we also discuss statistical methods for comparing predictive accuracy, as well as economic significance measures. In the empirical tests, we use data on the daily and weekly returns of the PX-50, BUX, WIG, and DAX stock exchange indices for the 2000–2006 period. We find neural networks to have a significantly lower prediction error than the classical models for the daily DAX series and the weekly PX-50 and BUX series. We also achieve economic significance of the predictions for both the daily and weekly PX-50, BUX, and DAX, with a 60% prediction accuracy.

Partners

Deloitte

Sponsors

CRIF
McKinsey
Patria Finance