Support Vector Machines for Prediction of Futures Prices in Indian Stock Market

Abstract

Machine learning methods are being used by several researchers for successfully predicting prices of financial instruments from the financial time series data of different markets. As the nature of markets in different regions are different, in this paper two machine learning techniques: Back Propagation Technique (BP) and Support Vector Machine Technique (SVM) have been used to predict futures prices traded in Indian stock market. The performances of these techniques are compared and it is observed that SVM provides better performance results as compared to BP technique. The implementation is carried out using MATLAB and SVM Tools (LS-SVM Tool Box). General Terms Machine Learning, Forecasting