Trend prediction of the Belex15 index and its constituents using LS-SVM

Abstract

Achieving profit through investing in the capital market is based on the ability to successfully predict future movements of the financial asset prices. Thus, the constant interest of investors in this particular field and emerging financial markets comes as no surprise, since these markets have been a relevant alternative source of investment opportunities for international investors. Our empirical study focuses on such an emerging market, the Belgrade stock exchange. Our main goal was to predict the direction of change of the Belex15 index and its most significant constituents. Firstly, we conducted detailed analysis of the most significant constituents of Belex15 index. Further analysis was realized using the Least Square Support Vector Machine (LS-SVMs) as a trend prediction model whereby feature selection was carried out through the analysis of technical indicators. The test results indicated that the proposed model gives better results for the constituents than for the Belex15 index itself.

Keywords

• ls-svm classification
• emerging markets
• belex15
• stock market prediction