M.H Karimi Dastjerdi - Industrial Engineering and Management Systems Amirkabir University of Technology Tehran, Iran
Mahdi Mirjalili - Industrial Engineering and Management Systems Amirkabir University of Technology Tehran, Iran
Pejman Mehran - Industrial Engineering and Management Systems Amirkabir University of Technology Tehran, Iran

Predicting the future values of time series (signals) based on the past and present data can be a useful tool for financial applications. In this study, the stock index prediction is made using a hybrid model, composed of the wavelet transform and NonlinearAuto-Regressive with eXogenous Inputs (NARX) neural network. This model comprises two stages. First, the preprocessing stage in which the Haar wavelet transform and a soft thresholdingapproach are used to de-noise the macroeconomic variables (oil prices and Rial to Dollar exchange rate). Second, the NARX neural network is developed to use the de-noised external inputs topredict the stock index as the output. By comparing the results of NARX neural network and the hybrid model, it is shown that the proposed model is more accurate than NARX neural network, and can achieve more reliable results.

Stock index forecasting; Hybrid model; Wavelet transform; NARX neural networks