Application of Support Vector Machine Regression in Stock Price Forecasting

Abstract

An investigation into how support vector machine can be used in the regression process of financial forecasting. A novel stock pricing model has been proposed based on the well-developed fundamental factors model and a combination of factors used in the model have been carefully selected to predict the common stock price. Several classical regression techniques therefore are applied separately in the predicting process and comparison has been made on the correctness of the predicted result. Support Vector Machine Regression has shown very strong competitivity throughout the test.