Stock market prediction is considered as a challenging task in the area of forecasting of financial time series. The main reason for this is the lack of certainty about how the stock market moves. Stock price data analysis is difficult due to the nonlinearity and the high noise level. The purpose of this paper is to forecast the capital market using the improved gray prediction pattern in Tehran Stock Exchange. For this purpose, the total stock price index (TEPIX) was used. The obtained results indicated that the improved gray algorithm fitted with minimizing the prediction error is an appropriate algorithm for predicting the fluctuation of the total stock price index. Stock market prediction is considered as a challenging task in the area of forecasting of financial time series. The main reason for this is the lack of certainty about how the stock market moves. Stock price data analysis is difficult due to the nonlinearity and the high noise level. The purpose of this paper is to forecast the capital market using the improved gray prediction pattern in Tehran Stock Exchange. For this purpose, the total stock price index (TEPIX) was used. The obtained results indicated that the improved gray algorithm fitted with minimizing the prediction error is an appropriate algorithm for predicting the fluctuation of the total stock price index.