Chart Patterns Recognition and Forecast Using Wavelet and Radial Basis Function Network
Technical analysis mainly focuses on analyzing the chart patterns, which is a non-trivial task. Because one time scale alone cannot be applied to all analytical processes, the identification of typical patterns on a stock price chart requires considerable knowledge and experience. The last two decades has seen attempts to solve such non-linear financial forecasting problems using AI technologies such as neural networks, fuzzy logic, genetic algorithms and expert systems but these, although accurate, lack explanatory power or are dependent on domain experts. This paper introduces a case based reasoning (CBR) system that provides an explainable method of financial forecasting  that is not dependent on the inputs of domain experts. This study proposes an algorithm, PXtract, which identifies and analyses possible chart patterns, makes dynamic use of different time windows, and introduces a wavelet multi-resolution analysis incorporated within a radial basis function neural network (RBFNN) matching method that can be used to automate the chart pattern matching process.
Unable to display preview. Download preview PDF.
- 1.Austin, M., Looney, C., Zhuo, J.: Security market timing using neural networks. The New Review of Applied Expert System (2000)Google Scholar
- 2.Funabashi, M., Maeda, A., Morooka, Y., Mori, K.: Fuzzy and Neural Hybrid Expert Systems. Synergetic AI, IEEE Expert, 32–40 (1997)Google Scholar
- 3.Boris, K., Evgenii, V.: Data Mining in Finance – Advances in Relational and Hybrid Methods. Kluwer Academic Publishers, Dordrecht (2000)Google Scholar
- 4.Liu, J.N.K., Leung, T.T.S.: A Web-based CBR agent for financial forecasting a workshop program. In: 4th International Conference on Case-Based Reasoning, Vancouver, CA, pp. 243–253 (2001)Google Scholar
- 5.Bensignor, R.: New Thinking in Technical Analysis. Bloomberg Press (2000)Google Scholar
- 6.Thomas, N.B.: Encyclopedia of Chart Patterns. John Wiley & Sons, Chichester (2000)Google Scholar
- 10.Chang, F.-J., Liang, J.M., Chen, Y.-C.: Flood Forecasting using RBF Neural Networks. IEEE Transaction on SMC Part C 31(4), 530–535 (2001)Google Scholar
- 11.Ng, H.S., Lam, K.P., Lam, S.S.: Incremental genetic fuzzy expert trading system for derivatives market timing. In: Proceeding of IEEE 2003 International Conference on Computational Intelligence for Financial Engineering, Hong Kong (2003)Google Scholar
- 13.Blakey, P.: Pattern recognition techniques [in stock price and volumes]. Microwave magazine, IEEE 3(1), 23–28 (2002)Google Scholar
- 15.Phua, P.K.H., Zhu, X., Koh, C.H.: Forecasting stock index increments using neural networks with trust region methods. In: Proceedings of the International Joint Conference on Neural Networks, vol. 1, pp. 260–265 (2003)Google Scholar
- 16.Qi, M.: Forecasting real time financial series. In: Proceedings of the 2002 International Joint Conference on Neural Networks, vol. 1, pp. 377–381 (2002)Google Scholar
- 17.Liu, J., Kwong, R.: Chart Patterns Extraction and Recognition in CBR System for Financial Forecasting. In: Proceeding of the IASTED International Conference ACI 2002, Tokyo, Japan, pp. 227–232 (2002)Google Scholar