Design and Implementation of Artificial Neural Network System for Stock Exchange Prediction

Stock prediction with artificial neural network (ANN) techniques is one of the most important issues in finance being investigated by researchers across the globe. ANN techniques can be used extensively in the financial markets to help investors make qualitative decision. In this methodology a multilayer perception (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 statistical and parametric models like as multiple regression and other traditional statistical techniques. This study and test also show that useful predictions can be made without the use of extensive market data or knowledge, and in the data mining process, neural networks and some non algorithmic models can explore high level orders in complex time series which hide in the market structure and need very huge calculations in normal conditions. Our study was including of a relatively extensive range of indexes stock market prices in Iran. We've made two different predictions in Tehran Stock Exchange (TSE), and by help ANN and a new method of data mining, indexes stock market prices with about 1% error level, we predict.