Forecasting FTSE Bursa Malaysia KLCI trend with Hybrid Particle Swarm Optimization and Support Vector Machine technique

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 performance of SVM can be affected by the high dimensional 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 optimization of the gamma and large margin parameters are done using the PSO algorithm. The proposed algorithm was tested on a pre-sampled 17 years record of daily Kuala Lumpur Composite Index (KLCI) data. The PSOSVM approach is applied to eliminate unnecessary or insignificant features, and effectively determine the parameter values, in turn improving the overall prediction results. The optimized feature space of technical indicators of the algorithm is proven by the experimental results showing that PSOSVM has outperformed SVM technique significantly.