Forecasting FTSE Bursa Malaysia KLCI Trend with Hybrid Particle Swarm Optimization and Support Vector Machine Technique

Lee, Zhong Zhen and Choo, Yun Huoy and Draman @ Muda, Azah Kamilah and Abraham, Ajith (2013) Forecasting FTSE Bursa Malaysia KLCI Trend with Hybrid Particle Swarm Optimization and Support Vector Machine Technique. In: 2013 World Congress on Nature and Biologically Inspired Computing (NaBIC), 12-14 Aug. 2013, Fargo, USA.

Text Nabic2013.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Stock trend forecasting is one of the important issues in stock market research. However, forecasting stock trend remains a challenge because of its irregular characteristic in the stock indices distribution, which changes over time. Support Vector Machine (SVM) produces a fairly good result in stock trend forecasting, but the perform ance of SVM can be affected by the high dim ensional input features and noisy data. This paper hybridizes the Particle Swarm Optimization (PSO) algorithm to generate the optimum features set prior to facilitate SVM learning. The SVM algorithm uses the Radial Basis Function (RBF) kernel function and optim ization of the gam ma and large margin parameters are done using the PSO algorithm. The proposed algorithm was tested on a pre-sam pled 17 years record of daily Kuala Lumpur Com posite Index (KLCI) data. The PSOSVM approach is applied to elim inate unnecessary or insignificant features, and effectively determ ine the param eter values, in turn improving the overall prediction results. The optimized feature space of technical indicators of the algorithm is proven by the experim ental results showing that PSOSVM has outperform ed SVM technique significantly.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Faculty of Information and Communication Technology > Department of Industrial Computing
Depositing User:	Dr. Yun-Huoy Choo
Date Deposited:	11 Feb 2014 07:48
Last Modified:	23 May 2023 12:53
URI:	http://eprints.utem.edu.my/id/eprint/11059
Statistic Details:	View Download Statistic

Actions (login required)

View Item