A comparison between Hybrid Approaches of ANN and ARIMA for Indian Stock Trend Forecasting

In this paper an attempt is made to develop hybrid models of three layer feed forward back propagation artificial neural network (ANN( and autoregressive integrated moving average (ARIMA) for forecasting the future index value and trend of Indian stock market viz. SENSEX, BSE IT, BSE Oil & Gas, BSE 100 and S& P CNX Nifty. Simulations have been done using prices of daily open, high, low and close of SENSEX, BSE IT, BSE Oil & Gas, BSE 100 and S& P CNX Nifty. These are chosen as input data values and output is the forecasted closing price of SENSEX, BSE IT, BSE Oil & Gas, BSE 100 and S& P CNX Nifty for the next day and future trend. Simulation results of hybrid models are compared with results of ANN based models and ARIMA based models. Convergence and performance of models have been evaluated on the basis of the simulation results done on MATLAB 6.1 and SPSS 13.0.