Samira Bastami - Naraq Branch, Islamic Azad University, Naraq, Iran
Mehdi Ghafari - Naraq Branch, Islamic Azad University, Naraq, Iran

Time series analysis is somewhat parallel to technical analysis, but it differs from the latter by using different statistical methods and models to analyze historical stock prices and predict the future prices. With the rapid increases in algorithmic or high frequency trading in which trader make trading decisions by analyzing data patterns rather than fundamental factors affecting stock prices, both technical analyses and time series analyses become more relevant. In this research, forecasting stock prices using artificial neural networks are evaluated. The goal of this research is to predict total stock market index of Tehran Stock Exchange, using the compound method of OLS, ARCH and neural network. Prediction in any field is a complicated, challenging and daunting process. Employing traditional methods may not ensure the reliability of the prediction. In this paper, we are reviewing the possibility of applying two well-known techniques neural network and data mining in stock market prediction. As neural network is able to extract useful information from a huge data set and data mining is also able to predict future trends and behaviors. Therefore, a combination of both these techniques could make the prediction much reliable.

Artificial Neural Network (ANN), TEPIX, OLS, ARCH