Publication detail

Vacha L., Barunik J.: Wavelet Neural Networks Prediction of Central European Stock Markets

Author(s): doc. PhDr. Jozef Baruník Ph.D.,
Mgr. Lukáš Vácha Ph.D.,
Type: Article in collection
Year: 2008
Number: 0
ISSN / ISBN: 978-80-8078-217-7
Published in: Quantitative Methods in Economics proceedings
Publishing place:
Keywords: neural networks, hard threshold denoising, time series prediction, wavelets
JEL codes:
Suggested Citation:
Grants: GAUK 46108: New Nonlinear Capital Markets Theories: Fractal, Bifurcational and Behavioral Approach
Abstract: In this paper we apply neural network with denoising layer method for forecasting of Central European Stock Exchanges, namely Prague, Budapest and Warsaw. Hard threshold denoising with Daubechies 6 wavelet filter and three level decomposition is used to denoise the stock index returns, and two-layer feed-forward neural network with Levenberg-Marquardt learning algorithm is used for modeling. The results show that wavelet network structure is able to approximate the underlying process of considered stock markets better that multilayered neural network architecture without using wavelets. Further on we discuss the impact of structural changes of the market on forecasting accuracy, and we find that for certain periods the one-step-ahead prediction accuracy of the direction of the stock index can reach 60% to 70%.

Partners

Deloitte

Sponsors

CRIF
McKinsey
Patria Finance