.
Forecasting stock prices using neural networks
Artificial neural network (Ann) has been shown to be an efficient tool for Non-parametric modeling of data in a
variety of different contexts where the output is a non-linear function of the inputs. These include business forecasting, Credit scoring, bond rating, business failure prediction, medicine, pattern recognition and image processing. A large number of studies have been reported in the literature with reference to use of Ann in modeling stock prices in the western countries. However, not much work along these lines has been reported in the Indian context. In this study we discuss modeling of Indian stock market (price index) data using Artificial Neural Networks for short term predictions. We study the efficacy of Ann in modeling the daily closing price values of the companies listed on Bombay stock exchange (bse) or on National Stock Exchange (NSE) viz. NTPC Ltd, Reliance Energy Ltd, BHEL, ONGC, IOC. Different networks are developed for different companies each using a consistent set of lags as input variable. The Neural Networks are trained using past data say nearly past two years. To assess the performance of the networks we used them to predict the daily closing values of the companies aforementioned for the one year period beginning January 2007. The mean absolute error (MAE) is chosen as the indicators of the performance of the networks.
The results show that artificial neural networks are an emerging and promising computational technology that will continue to be a challenging tool for future research.
Published: January 25, 2008