<![CDATA[The purpose of this study is to find out the best forecasting method to overcome the gap between the demand for roasted coffee desired by consumers and the production fulfilled by the company. The data used is secondary data in the form of reports on the production and sales of roasted coffee Perumda Kahyangan Jember Plantation. The sample used in this study was 24 sales data of roasted coffee per month with purposive sampling techniques. The forecasting model used in this study is Time Series consisting of Naive, Moving Average methods, and Exponential Smoothing with a Mean Absolute Percentage Error (MAPE) measuring instrument as a standard reference for measuring forecasting errors. The results showed that the 4-month Moving Average method is the best forecasting method. This is based on the measurement of the forecasting error of the MAPE value of 13%. The lower the percentage error in MAPE, the more accurate the forecasting results. From the results of the study, it can be concluded that the Moving Average method for a period of 4 months can be used as a reference for companies in determining roasted coffee production in the next period, which is 2,248.75 kg. Keywords: Exponential Smoothing; MAPE; Moving Average; Naive; Forecasting; Time Series]]>
Copyrights © 2023
