Forecasting Indian Stock Market Using Artificial Neural Networks

The objective of this research is to predict the next day's opening value of Nifty-100 index of the National Stock Exchange (NSE) using Artificial Neural Networks (ANNs). The ANN is trained using Error Backpropagation Training Algorithm (EBPTA). The multilayer feedforward network is trained using the present day's closing values of seven input parameters which are Gold, Silver, Copper, Crude Oil, Natural Gas and Foreign Exchange (FOREX) rates. In addition to these six rates, the closing value of Nifty-100 index was incorporated as input using Simple Moving Average (SMA) model. The relationship between each input parameter and Nifty-100 index was studied and analyzed using correlation technique. This research proves that Nifty-100 index can be predicted using ANNs.