Performance Analysis of the Multivariate Multiple Linear Regression Algorithm for Economic Growth Based on Oil Palm Plantation Land Expansion in North Sumatra Province

Afridayani (Master of Data Science and Artificial Intelligence, Faculty of Computer Science and Information Technology, Universitas Sumatera Utara, Indonesia)
Erna Budhiarti Nababan (Master of Data Science and Artificial Intelligence, Faculty of Computer Science and Information Technology, Universitas Sumatera Utara, Indonesia)
Baihaqi Siregar (Master of Data Science and Artificial Intelligence, Faculty of Computer Science and Information Technology, Universitas Sumatera Utara, Indonesia)

Green Intelligent Systems and Applications
Volume 6 - Issue 2 - 2026

Oil palm plantations are one of the main sectors contributing to regional economic development in North Sumatra Province. This study aimed to analyze the performance of the Multivariate Multiple Linear Regression (MMLR) algorithm in modeling the relationship between oil palm plantation expansion and regional economic indicators. Secondary data from five oil palm-producing regencies covering the period 2013–2023 were obtained from the Central Statistics Agency (BPS). The independent variables consisted of plantation area and oil palm production, whereas the dependent variables were Gross Regional Domestic Product (GRDP) and per capita income. The dataset was divided into training (2013–2019) and testing (2020–2023) subsets. Model performance was evaluated using the coefficient of determination (R²), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The results showed that the MMLR model was able to capture the relationship between oil palm plantation expansion and regional economic indicators, although its predictive performance varied across regencies. These findings indicated that the model provided useful insights into the contribution of the oil palm plantation sector to regional economic development in North Sumatra.