<![CDATA[PT XYZ still implements a manual inventory recording process, potentially causing stock discrepancies that can disrupt the company's operational flow. This study aims to predict inventory needs to support more accurate stock control. The data used are historical purchase and inventory data for the period April–September 2025. The analysis was conducted using three time series methods, namely Moving Average (MA), Exponential Smoothing (ES), and Autoregressive Integrated Moving Average (ARIMA). The analysis stages include identifying data patterns, model formation, parameter testing, forecasting inventory needs, and evaluating model accuracy using Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE). The model with the smallest error value was selected as the best model to determine stock needs, Safety Stock, and Reorder Point. The results showed that the ARIMA (1,1,1) model provided the best level of accuracy with an MAE value of 98.71, MAPE 7.25%, and RMSE 124.46. Based on this model, the estimated inventory requirement for the next period is 1,312 units, with a safety stock of 152 units and a reorder point of 1,458 units. The analysis results are visualized in a dashboard, showing that the majority of inventory is in the safe category, thus supporting more effective inventory control.]]>
Copyrights © 2026
