A novel approach to predict stock market price using radial basis function network

In the financial sector, the sales price forecasting is a hot issue. Since the indices associated with the stock are nonlinear and are affected by various internal and external factors, they are very difficult to model and pose a difficult problem to be solved by the researchers. This paper is devoted in designing an intelligent prediction model based on the radial basis function network (RBFN). To tune its parameters a learning algorithm is developed using the back-propagation (BP) method. The performance of the proposed method is also compared with that of the multi-layered feed-forward neural network (MLFFNN) containing only single hidden layer and the results obtained from the simulation study indicate that the performance of RBFN is better as compared to the MLFFNN model.