Predicting Changes in Stock Index and Gold Prices to Neural Network Approach

This paper presents a study of artificial neural networks for use in stock price prediction. The data from an emerging market, Tehran’s Stock Exchange (T.S.E), are applied as a case study. Based on the rescaled range (R/S) analysis, the behavior of stock price has been studied. R/S analysis is able to distinguish a random series from a non-random one. It is used to detect the long-memory effect in the TEPIX time series. It is shown that the behavior of stock price is non-random and short-term prediction of the TEPIX is possible, and modeling of stock price movements can be done. A multilayer perceptron (M.L.P) neural network model is used to determine and explore the relationship between some variables as independent factors and the level of stock price index as a dependent element in the stock market under study over time. The results show that the neural network models can get better outcomes compared with parametric models like regression and others traditional statistical techniques. Our test also shows that useful predictions can be made without the use of extensive market data or knowledge, and in the data mining process, neural networks can explore some orders which hide in the market structure.