Abstract
In this article, a short introduction into the field of pattern recognition in time series has been given. Our goal is to find and recognize important patterns which repeatedly appear in the market history. We focus on reliability of recognition made by the proposed algorithms with optimized patterns based on artificial neural networks. The performed experimental study confirmed that for the given class of tasks can be acceptable a simple Hebb classifier with a proposed modification that has been designed, tested, and used for the active mode of Hebb rule. Finally, we present comparison results of trading based on both recommendations: using proposed Hebb neural network implementation, and human expert.
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.
Similar content being viewed by others
References
Anand, S., Chin, W.N., Khoo, S.C.: Chart Patterns on Price History. In: Proc. of ACM SIGPLAN Int. Conf. on Functional Programming, Florence, Italy, pp. 134–145 (2001)
Bulkowski, N.: Encyclopedia of Chart Patterns, 2nd edn. John Wiley and Sons (2005)
Ciskowski, P., Zaton, M.: Neural Pattern Recognition with Self-organizing Maps for Efficient Processing of Forex Market Data Streams. AISC, pp. 307–314 (2010), doi:10.1007/978-3-642-13208-7_39
Dormido-Canto, S., Farias, G., Vega, J., Dormido, R., Sánchez, J., Santos, M., et al.: Search and retrieval of plasma waveforms: structural pattern recognition approach. Review of Scientific Instruments 77, 10F514 (2006)
Fausett, L.V.: Fundamentals of Neural Networks. Prentice-Hall, Inc., Englewood Cliffs (1994)
Frost, A.J., Prechter, R.: Elliott wave principle: key to market behavior, 7th edn. New Classics Library, Gainesville (1998)
Gershenson, C.: Design and Control of Self-organizing Systems. Dissertation. Vrije Universiteit Brussel (2007)
Kamijo, K., Tanigawa, T.: Stock Price Pattern Recognition: A Recurrent Neural Network Approach. In: Proc. of the Int. Joint Conf. on Neural Networks, vol. 1, pp. 215–221 (1990)
Kocian, V., Volna, E., Janosek, M., Kotyrba, M.: Optimizatinon of training sets for Hebbian-learningbased classifiers. In: Matoušek, R. (ed.) Proceedings of the 17th International Conference on Soft Computing, Mendel 2011, Brno, Czech Republic, pp. 185–190 (2011) ISBN 978-80-214-4302-0, ISSN 1803-3814
Leigh, W., Modani, N., Hightower, R.: A Computational Implementation of Stock Charting: Abrupt Volume Increase As Signal for Movement in New York Stock Exchange Composite Index. Decision Support Systems 37(4), 515–530 (2004)
Volna, E., Janosek, M., Kotyrba, M., Kocian, V., Oplatkova, Z.: Methodology for System Adaptation based on Characteristic patterns. In: Dutta, A. (ed.) Robotic Systems – Applications, Control and Programming, pp. 611–628. InTech, Croatia (2012) ISBN 978-953-307-941-7
X-Trader Brokers, http://xtb.cz (accessed September 3, 2011)
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
Volna, E., Janosek, M., Kotyrba, M., Kocian, V. (2013). Pattern Recognition Algorithm Optimization. In: Zelinka, I., Rössler, O., Snášel, V., Abraham, A., Corchado, E. (eds) Nostradamus: Modern Methods of Prediction, Modeling and Analysis of Nonlinear Systems. Advances in Intelligent Systems and Computing, vol 192. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33227-2_26
Download citation
DOI: https://doi.org/10.1007/978-3-642-33227-2_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33226-5
Online ISBN: 978-3-642-33227-2
eBook Packages: EngineeringEngineering (R0)