<![CDATA[Fluctuating blood bag demand and the limited shelf life of blood necessitate accurate inventory planning to support blood transfusion services. This study aims to determine the most accurate Exponential Smoothing model for forecasting blood bag demand at the PMI Blood Transfusion Unit in Sumbawa Regency. The study employed a quantitative approach using time-series analysis on biweekly blood bag demand data from January 2019 to November 2025, applying the Single Exponential Smoothing, Double Exponential Smoothing, and Holt–Winters Exponential Smoothing methods, which were then evaluated based on MAPE, MSE, RMSE, AIC, and BIC. The results of the study show that blood demand data exhibits a downward trend with a weak seasonal component. Based on accuracy evaluations, the best model varies by blood type. For blood type A, the DES method was selected based on the lowest MSE and RMSE values, and the SES method was selected based on the lowest AIC and BIC values. For blood type O, the SES method provided the best performance based on the accuracy evaluation results. Forecasts for 2026 indicate that the demand for blood bags of blood groups A and O is expected to decline. These findings suggest that the selection of forecasting methods needs to be tailored to the characteristics of the data in order to support more effective blood inventory planning at the PMI Blood Transfusion Unit in Sumbawa Regency.]]>
Copyrights © 2026
