Using the Event Classifier System to Forecast the Stock Price: An Empirical Study of Taiwan Financial Market

Abstract:

This study was meant to construct an intelligent financial investment decision-making system capable of knowledge mining, performing assessments and evolving on its own based on event assessments by applying the classifier system in the artificial intelligence methodology. It is referred to as the Event Classifier System (ECS). In order to prove the feasibility and validity of the developed method and model, this study designed and developed the transaction model for event classifiers by creating the strategic modules for institutional investor’s holdings-related events and ex-right (dividend)-related events. Results of this empirical study show that the ECS established in this study had superior return on investment (ROI) performance than the Taiwan Weighted Stock Index for the same period of time.

• Periodical: Applied Mechanics and Materials (Volumes 764-765)
• Pages: 1400-1406
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.764-765.1400
• Online since: May 2015
• Authors: Chien Hua Huang*, Janq Lin Yo, An Pin Chen
• Keywords: Classifier System, Event Assessment, Event Valuation, Knowledge Mining, Stock Transaction

References

[1] E.F. Fama: Efficient Capital Market: A View of Theory and Empirical Work. Journal of Finance 25 (1970) 383-417.

[2] J.H. Holland: Processing and processors for Schemata, in E.L. Jacks (Ed. ), Associative information processing, American Elsevier, New York, 1971, pp.127-146.

[3] J.H. Holland: A Mathematical Framework for Studying Learning in Classifier Systems. Physica 2(1-3) (1986) 307-317.

[4] S.W. Wilson, D.E. Goldberg: A Critical Review of Classifier Systems. In Proceedings of the 3rd International Conference on Genetic Algorithms, 244-255, Morgan Kauffman, (1989).

[5] S.W. Wilson: ZCS: A zeroth level classifier system. Evolutionary Computation 2(1) (1994) 1-18.

DOI: 10.1162/evco.1994.2.1.1

[6] S.W. Wilson: Classifier Fitness Based on Accuracy, Evolutionary Computation 3(2) (1995)149-175.

[7] A.P. Chen, Y.C. Chen and W.C. Tseng: Applying Extending Classifier System to Develop an Option-Operation Suggestion Model of Intraday Trading-An Example of Taiwan Index Option, Lecture Notes in AI 3681 (2005a) 27-33.

DOI: 10.1007/11552413_5

[8] A.P. Chen, Y.C. Chen and Y.H. Huang: Applying Two-Stage XCS Model on Global Overnight Effect for Local Stock Prediction. Lecture Notes in AI 3681 (2005b) 34-40.

DOI: 10.1007/11552413_6

[9] Y.K. Tsai: Applying Classifier Systems in Financial Distress Prediction Modeling. Master Thesis, National Chiao Tung University, (2004).