This research deals with the comparative examination of applying artificial neural networks and auto regression model and its influence in declining prediction error of Tehrans stock market index. The basic subject of the research is to find a method to the better prediction of stock price. Statistical societies of this study are those companies accepted in Tehrans stock market during 2006 –2012 .Statically sample of the research equals to the statistical society .Required data are gathered by library studies for research literature and by country stock market organization software’s for variables.