Abstract
In this study, a novel adaptive learning algorithm for feed-forward network based on optimized instantaneous learning rates is proposed to predict stock market movements. In this new algorithm, the optimized adaptive learning rates are used to adjust the weight changes dynamically. For illustration and testing purposes the proposed algorithm is applied to two main stock price indices: S&P 500 and Nikkei 225. The experimental results reveal that the proposed algorithm provides a promising alternative to stock market prediction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Widrow, B., Lehr, M.A.: 30 Years of Adaptive Neural Networks: Perception, Madaline, and Backprpagation. Proceedings of the IEEE Neural Networks I: Theory & Modeling 78(Special issue), 1415–1442 (1990)
Rumelhart, D.E., McClelland, J.L.: Parallel Distributed Processing. MIT Press, Cambridge (1986)
Tollenaere, T.: SuperSAB: Fast Adaptive Back Propagation with Good Scaling Properties. Neural Networks 3, 561–573 (1990)
Park, D.C., El-Sharkawi, M.A., Marks II, R.J.: An Adaptive Training Neural Network. IEEE Transactions on Neural Networks 2, 334–345 (1991)
Jacobs, R.A.: Increase Rates of Convergence through Learning Rate Adaptation. Neural Networks 1, 295–307 (1988)
Brent, R.P.: Fast Training Algorithms for Multilayer Neural Nets. IEEE Transactions on Neural Networks 2, 346–354 (1991)
Hagan, M.T., Menhaj, M.: Training Feedforward Networks with Marquardt Algorithm. IEEE Transactions on Neural Networks 5, 989–993 (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yu, L., Wang, S., Lai, K.K. (2005). A Novel Adaptive Learning Algorithm for Stock Market Prediction. In: Deng, X., Du, DZ. (eds) Algorithms and Computation. ISAAC 2005. Lecture Notes in Computer Science, vol 3827. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11602613_45
Download citation
DOI: https://doi.org/10.1007/11602613_45
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-30935-2
Online ISBN: 978-3-540-32426-3
eBook Packages: Computer ScienceComputer Science (R0)