Stock Market Prediction by Non-Linear Combination based on Support Vector Machine Regression Model

Abstract

Stock market predictions comprise challenging applications of modern time series forecasting and are essential to the success of many
businesses and financial institutions. In this paper, stock market forecasting is based on Support Vector Machine (SVM) regression. Firstly,
using different linear regression model to extract linear characteristics of stock market system. Secondly, using different Neural Network
algorithms to extract nonlinear characteristics of stock market system. Finally, the SVM regression is used for the nonlinear combination
forecasting model of different stock exchange prices. Empirical results obtained reveal that the prediction by using the nonlinear combination
model is generally better than those obtained using other models presented in this study in terms of the same evaluation measurements. Those
results show that that the proposed nonlinear modeling technique is a very promising approach to financial time series forecasting.

Keywords: Linear Regression, Neural Network, Support Vector Machine, Forecasting.