<![CDATA[Purpose – Crude Palm Oil (CPO) production fluctuates with Fresh Fruit Bunches (FFB) supply and operational conditions, making production planning difficult for palm oil mills. This study develops a CPO production prediction information system that integrates a simple linear regression model into a Progressive Web Application (PWA) to provide an accessible decision-support tool. Methods – The study used 39 monthly production records from PTPN IV Regional II Adolina Palm Oil Mill, covering January 2023 to March 2026. FFB was used as the independent variable and CPO production as the dependent variable. The model was developed using simple linear regression, evaluated through an 80/20 train-test split, MAE, RMSE, and R², and implemented in a PWA-based system using PHP and MySQL. Findings – The regression model produced the equation Y = -101.869 + 0.238X. The model achieved R² = 0.872, MAE = 279.80 tons, and RMSE = 335.72 tons. With average monthly CPO production of 2,000–3,000 tons, the MAE represents an approximate error rate of 10–14%, indicating moderate predictive performance. Research implications – The findings are useful for preliminary production planning, but generalization is limited by the use of one predictor, 39 observations, one palm oil mill, and the absence of k-fold cross-validation. Originality – This study contributes by combining an interpretable linear regression model with a PWA-based system for real-time CPO prediction and visualization.]]>
Copyrights © 2026
