The aim of this research is to determine the amount of production forecasting Golden Cain Erro Mella and to determine the level of errors in forecasting. Discussion of the method used to predict the amount of production is the average Moving Average - 3 month moving average and exponential Smoothing five months and with three different values α ; 0.1, 0.5, 0.9. Comparison of forecasting methods and to find the method that has the smallest level of the Mean Squared Error. Selected forecasting methods used to forecast the total production fabrics of Erro Golden Mella in March 2010. From the data have been analyzed, the authors can conclude that the magnitude of the forecast total production in the months of March 2010 using a Single Moving Average Method 3 months amounted to 617 333 yards with MSE 74.67382 billion, while the period of five monthly forecasts obtained for 594 400 yards, with MSE 83.02392 billion and magnitude of the forecast total production in March 2010 when calculated using the method of exponential Smoothing with three values are (1) value α 0,1 are 756.858 yard, with MSE 94.629.450.000. (2) value α 0,5 are 674.729 yard, with MSE are 57.274.280.000. (3) value α 0,9 are 815.019 yard with MSE 64.479.990.000.