The demand for Piston Cup Forging in spare-part companies every period has increased and decreased, which causes uncertainty about product demand. In this case, the company needs to do demand forecasting. There are various methods of doing forecasting. Companies must choose the best forecasting method, so that companies can make decisions more effectively and efficiently. This research aims to compare the best forecasting methods to apply for companies. The methods that will be compared in this research are Moving Average 3 monthly and 5 monthly, and Exponential Smoothing with α = 0,1; α = 0,5; and α = 0,9. The error accuracy calculations used are Mean Absolute Deviation (MAD), Mean Squared Error (MSE), and Mean Absolute Percentage Error (MAPE). From the results of calculations and analysis, the method that has the lowest error rate is the Exponential Smoothing method with α = 0,1, with MAD of 16.695, MSE of 510.645.732, and MAPE value of 61%. So in estimating the demand for Piston Cup Forging over the upcoming period in spare-part companies can use the Exponential Smoothing method with α = 0,1.