PT. XYZ is one of the premium tea producers that manufactures products for export markets. Forecasting the inventory of palm kernel shells used as biomass fuel at PT. XYZ is essential to ensure that production fuel requirements are met accurately, support decision-making based on forecasting results, and maintain production capacity readiness. Several forecasting methods were applied, including Moving Average, Exponential Smoothing, Linear Regression, and Double Exponential Smoothing. The accuracy of these methods was evaluated using the Mean Absolute Error (MAE), and the results showed that the Linear Regression method achieved the lowest MAE, making it the best forecasting method. Based on this method, the forecasted demand for palm kernel shells was determined for the next six periods.
Copyrights © 2026