Binarized Genetic Algorithm with Neural Network for Stock Market Prediction

Abstract

Stock market prediction is a challenging task to predict the upcoming stock values. It is very difficult to predict because of unstable nature of stock. This stock market prices are continuously changing day by day. Many Business Analysts spends more money on this stock market. Some of the persons may lose the money on this stock market because they don't have clear idea about the stock market. Estimate and analyse the stock market accurately then only get more profit. Artificial neural network is a very popular technique for forecast the stock market price, but using this technique to forecast the stock market price up to some extent. So there is a need to improve the accuracy of the system. In this paper, propose a novel system called Binarized Genetic Algorithm with Artificial Neural Network (BGANN) technique to predict and forecast future behavior of individual stocks or the upcoming stock. Binarized Genetic Algorithm is used for optimizing Neural Network weights while training. Comparative analysis shows that BGANN method performance is better compared to the Support Vector Machine (SVM), Neural Network (NN), and Auto Regressive Integrated Moving Average (ARIMA) models.