Predicting the Direction of Stock Markets Employing Back Propagation in Neural Networks

Abstract

Stock Market prediction is a category of time series prediction which extremely challenging due to the dependence of stock prices on several financial, socio-economic and political parameters etc. Moreover, small inaccuracies in stock market price predictions may result in huge losses to firms which use stock market price prediction results for financial analysis and investments. Off late, artificial intelligence and machine learning based techniques are being used widely for stock market prediction due to relatively higher accuracy compared to conventional statistical techniques. The proposed work employs the steepest descent based scaled conjugate gradient (SCG) algorithm along with the data pre-processing using the discrete wavelet transform (DWT) for stock market prediction. It has been shown that the proposed system attains lesser mean square percentage error compared to previously existing technique. Keywords—Stock Market Forecasting, Artificial Neural Network (ANN), Back Propagation, Scaled Conjugate Gradient (SCG), Discrete Wavelet Transform (DWT), Mean Absolute Percentage Error (MAPE).