Prediction Method for Real Thai Stock Index Based on Neurofuzzy Approach
The prediction of financial market indicators is a topic of considerable practical interest and, if successful, may involve substantial pecuniary rewards. People tend to invest in equity because of its high returns over time. Stock markets are affected by many highly interrelated economic, political, and even psychological factors, and these factors interact in a very complex manner. Therefore, it is, generally, very difficult to forecast the movements of stock markets. Neural networks have been used for several years in the selection of investments. Neural networks have been shown to enable decoding of nonlinear time series data to adequately describe the characteristics of the stock markets . Examples using neural networks in equity market applications include forecasting the value of a stock index [2–5] recognition of patterns in trading charts [6, 7], rating of corporate bonds , estimation of the market price of options , and the indication of trading signals of selling and buying [10, 11], and so on. Feedforward backpropagation networks as discussed in Sect. 24.2 are the most commonly used networks and meant for the widest variety of applications.
The Stock Exchange of Thailand (SET) is the stock market in Thailand whereby stocks may be bought and sold. As with every investment, raising funds in the stock exchange entails some degree of risk. There are two types of risk: systematic risk and an erroneous one. The erroneous risk can be overcome by a sound investment strategy, called diversification. However, by using a better prediction model to forecast the future price variation of a stock, the systematic risk can be minimized if not totally eliminated.
This chapter describes a feedforward neural network and neurofuzzy system in Sect. 24.2. Subsequently, details for the methodology of stock prediction are explained in Sect. 24.3. Next, several results are presented involving neurofuzzy predictions in comparison to feedforward neural networks. Some conclusions based on the results presented in this chapter are drawn, with remarks on future directions.
KeywordsMembership Function Stock Market Stock Price Stock Index Closing Price
Unable to display preview. Download preview PDF.
- 1.Lapedes, A. and Farber, R.: Nonlinear signal processing using neural networks. IEEE Conference on Neural Information Processing System—Natural and Synthetic (1987). 101–107.Google Scholar
- 2.Yao, J.T. and Poh, H.-L.: Equity forecasting: A case study on the KLSE index, neural networks in financial engineering. Proceedings of 3rd International Conference on Neural Networks in the Capital Markets (1995). 341–353.Google Scholar
- 3.White, H.: Economic prediction using neural networks: A case of IBM daily stock returns. IEEE International Conference on Neural Networks, Vol. 2 (1998). 451–458.Google Scholar
- 6.Tanigawa, T. and Kamijo, K.: Stock price pattern matching system: Dynamic programming neural network approach. IJCNN’92, Vol. 2, Baltimore (1992). 59–69.Google Scholar
- 8.Dutta, S. and Shekhar, S.: Bond rating: A non-conservative application of neural networks. IEEE International Conference on Neural Networks (1990). 124–130.Google Scholar
- 9.Hutchinson, J.M., Lo, A., and Poggio, T.: A nonparametric approach to pricing and hedging derivative securities via learning networks. International Journal of Finance, Vol. 49 (1994). 851–889.Google Scholar
- 10.Chapman, A. J.: Stock market reading systems through neural networks: Developing a model. International Journal of Applying Expert Systems, Vol. 2, No. 2 (1994). 88–100.Google Scholar
- 12.Farber, J.D. and Sidorowich, J.J.: Can new approaches to nonlinear modeling improve economic forecasts? In The Economy As An Evolving Complex System. CA, Addison-Wesley (1988). 99–115.Google Scholar
- 13.LeBaron, B. and Weigend, A. S.: Evaluating neural network predictors by bootstrapping. In Proceedings of International Conference on Neural Information Processing (ICONIP’94), Seoul, Korea (1994). 1207–1212.Google Scholar
- 14.Doeksen, B., Abraham, A., Thomas, J., and Paprzycki, M.: Real stock trading using soft computing models. IEEE International Conference on Information Technology: Coding and Computing (ITCC’05) (2005). 123–129.Google Scholar
- 16.Trippi, R. and Lee, K.: Artificial Intelligence in Finance & Investing. Chicago: Irwin (1996).Google Scholar
- 17.Hiemstra, Y.: Modeling Structured Nonlinear Knowledge to Predict Stock Markets: Theory. Evidena and Applications, Chicago: Irwin (1995). 163–175.Google Scholar
- 20.Li, R.-J. and Xiong, Z.-B.: Forecasting stock market with fuzzy neural network. Proceedings of 4th International Conference on Machine Learning and Cybernetics, Guangaho (2005). 3475–3479.Google Scholar
- 21.Yoo, P.D., Kim, M.H., and Jan, T.: Machine learning techniques and use of event information for stock market prediction; A survey and evaluation. International Conference on Computational Intelligence for Modeling, Control and Automation, and International Conference of Intelligent Agents, Web Technologies and Internet Commerce (IMCA – IAWTIC 2005) (2005). 1234–1240.Google Scholar
- 22.Takagi, T. and Sugeno, M.: Fuzzy identification of systems and its application to modeling and control. IEEE Transaction on System Man and Cybernetics, Vol. 5 (1985). 116–132.Google Scholar
- 23.Babuska, R.: Neuro-fuzzy methods for modeling and identification. In Recent Advances in intelligent Paradigms and Application, New York: Springer-Verlag (2002). 161–186.Google Scholar
- 24.Correlation. Available: http://en.wikipedia.org/wiki/Correlation.