Abstract
In the present study, evolved neural network is applied to construct a new intelligent stock trading system. First, heterogeneous double populations based hybrid genetic algorithm is adopted to optimize the connection weights of feedforward neural networks. Second, a new intelligent stock trading system is proposed to generates buy and sell signals automatically through predicting a new technical indicator called medium term trend. Compared to traditional NN, the new model provides an enhanced generalization capability that both the average return and variance of performance are significantly improved.
This is a preview of subscription content, log in via an institution to check access.
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
Lin, X., Yang, Z., Song, Y.: Intelligent Stock Trading System Based on Improved Technical Analysis and Echo State Network. Expert Systems with Applications 38, 11347–11354 (2011)
Nunez-Letamendia, L.: Fitting the Control Parameters of A Genetic Algorithm: an Application on Technical Trading Systems Design. European Journal of Operational Research 179, 847–868 (2007)
Teixeira, L.A., Oliveira, A.L.I.D.: A Method for Automatic Stock Trading Combining Technical Analysis and Nearest Neighbor Classification. Expert Systems with Applications 37, 6885–6890 (2010)
Izumi, K., Toriumi, F., Matsui, H.: Evaluation of Automated-Trading Strategies Using an Artificial Market. NeuroComputing 72, 3469–3476 (2009)
Van Rooij, A.J.F., Jain, L.C., Johnson, R.P.: Neural networks training using genetic algorithms. In: Machine Perception and Artificial Intelligence, vol. 26. World Scientific, Singapore (1996)
Yao, X., Liu, Y.: A new evolutionary system for evolving artificial neural networks. IEEE Transactions on Neural Networks 8(3), 694–713 (1997)
Maniezzo, V.: Genetic evolution of the topology and weight distribution of neural networks. IEEE Transactions on Neural Networks 5(1), 39–53 (1994)
Su, C.-L., Yang, S.M., Huang, W.L.: A two-stage algorithm integrating genetic algorithm and modified Newton method for neural network training in engineering systems. Expert Systems with Applications 38, 12189–12194 (2011)
Teixeira, L.A., Oliveira, A.L.I.D.: A Method for Automatic Stock Trading Combining Technical Analysis and Nearest Neighbor Classification. Expert Systems with Applications 37, 6885–6890 (2010)
Zhao, S., Xu, G., Tao, T., Liang, L.: Real-coded chaotic quantum-inspired genetic algorithm for training of fuzzy neural networks. Computers and Mathematics with Applications 57, 2009–2015 (2009)
Balakrishnan, K., Honavar, V.: Evolutionary design of neural architectures—a pleliminary taxonomy and guide to literature, technical report CS TR#95-01. Artificial Intelligence Research Group, Department of Computer Science, Iowa State University, Ames, Iowa 50011-1040, USA (1995)
Zhang, L.F., He, R., Yan, M.L.: Heterogeneous double populations based hybrid genetic algorithm design for training feedforward neural networks. In: Proceedings of IEEE Congress on Evolutionary Computation (IEEE CEC 2012), Australia, Brisbane, June 10-15, p. 492 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, L., Sun, Y. (2013). Evolved Neural Network Based Intelligent Trading System for Stock Market. In: Tan, Y., Shi, Y., Mo, H. (eds) Advances in Swarm Intelligence. ICSI 2013. Lecture Notes in Computer Science, vol 7928. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38703-6_56
Download citation
DOI: https://doi.org/10.1007/978-3-642-38703-6_56
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38702-9
Online ISBN: 978-3-642-38703-6
eBook Packages: Computer ScienceComputer Science (R0)