<![CDATA[Oil palm is one of Indonesia’s leading commodities with a significant contribution to the national economy. Production fluctuations caused by environmental and technical factors require an accurate predictive model. This study aims to predict Fresh Fruit Bunch (FFB) production using the Random Forest Regression algorithm based on data from PT Perkebunan Nusantara IV Regional 1, Bandar Selamat Unit (2022–2024). The research employed historical data including land area, number of trees, plant density, bunch count, and planting year. The model underwent preprocessing, training, testing, and evaluation using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and coefficient of determination (R²). Results show that Random Forest Regression achieved excellent accuracy with R² = 0.9846, MAE = 31,889.58 kg, and RMSE = 55,164.62 kg. The most influential factors were planting year, number of trees, and land area. In conclusion, Random Forest Regression is highly effective for predicting oil palm production and captures complex non-linear relationships among variables.]]>
Copyrights © 2025
