A Novel Evolving Clustering Algorithm with Polynomial Regression for Chaotic Time-Series Prediction
Time-series prediction has been a very well researched topic in recent studies. Some popular approaches to this problem are the traditional statistical methods e.g. multiple linear regression and moving average, and neural network with the Multi Layer Perceptron which has shown its supremacy in time-series prediction. In this study, we used a different approach based on evolving clustering algorithm with polynomial regressions to find repeating local patterns in a time-series data. To illustrate chaotic time-series data we have taken into account the use of stock price data from Indonesian stock exchange market and currency exchange rate data. In addition, we have also conducted a benchmark test using the Mackey Glass data set. Results showed that the algorithm offers a considerably high accuracy in time-series prediction and could also reveal repeating patterns of movement from the past.
Keywordsevolving clustering algorithm polynomial regression chaotic time-series data
Unable to display preview. Download preview PDF.
- 5.Serguieva, A., Kalganova, T., Khan, T.: An intelligent system for risk classification of stock investment projects. Journal of Applied Systems Studies 4(2), 236–261 (2003)Google Scholar
- 6.Song, Q., Kasabov, N.: ECM – A Novel On-line Evolving Clustering Method and Its Applications. In: Posner, M.I. (ed.) Foundations of cognitive science, pp. 631–682 (2001)Google Scholar
- 8.Yang, H., Chan, L., King, I.: Support Vector Machine Regression for Volatile Stock Market Prediction. In: Yellin, D.M. (ed.) Attribute Grammar Inversion and Source-to-source Translation. LNCS, vol. 302, pp. 143–152. Springer, Heidelberg (1988)Google Scholar
- 9.Zanghui, Z., Yau, H., Fu, A.M.N.: A new stock price prediction method based on pattern classification. In: International Joint Conference on Neural Network 1999, pp. 3866–3870 (1999)Google Scholar