Application of GA with SVM for Stock Price Prediction in Financial Market

Time series forecasting is receiving remarkable attention from the research community in using data mining techniques to analyze the extensive historical datasets for solving prediction problems. For such type of forecasting the indicators are required to be derived from relevant time series. In stock price forecasting in the financial sector more than 100 indicators have been developed to understand stock market behavior and thus the identification of the right indicators is a challenging problem. In such a case, optimized computer algorithms need to be investigated and applied for identifying really necessary indicators. From the various machine learning techniques available one of the technique recently investigated for time series forecasting is the Support Vector Regression (SVR) or Support Vector Machine (SVM) [7]. This study applies GA-SVM to predict the stock price index. In addition, the study also examines the feasibility of applying GA-SVM in financial forecasting by comparing it with Support Vector Machine (SVM) and case-based reasoning. The experimental results show that SVM with GA provides a more optimized and promising alternative to stock market prediction.