A new architecture for modeling and prediction of dynamic systems using neural networks: application in Tehran stock exchange

Modeling and forecasting Stock market is a challenging task for economists and engineers since it has a dynamic structure and nonlinear characteristic. This nonlinearity affects the efficiency of the price characteristics. Using an Artificial Neural Network is a proper way to model this nonlinearity and it has been used successfully in one-step ahead and multi-step ahead prediction of different stock prices. Several factors, such as input variables, preparing data, network architecture and training procedure, have huge impact on the accuracy of the neural network prediction. The purpose of this paper is to derive a method for multi-step ahead prediction based on Recurrent Neural Networks (RNN), Real-Time Recurrent Learning (RTRL) networks and Nonlinear AutoRegressive model process with eXogenous input (NARX). The model is trained and tested by Tehran Securities Exchange data.