Using K-Means Clustering to Analyze Socio-Economic Welfare of Oil Palm Farmers for Decision Support and Contextual Learning Integration

This study aims to cluster the welfare levels of oil palm farmers in Gading Sari Village, Tapung, using the K-Means Clustering algorithm. The analyzed variables include land area, family dependents, average monthly income, additional income, and educational attainment. Previous studies have extensively discussed the welfare of oil palm farmers. This research uses clustering methods to uncover new and more detailed findings about the welfare of oil palm farmers in rural areas. This approach offers a fresh perspective and can be utilized to support data-driven decision-making processes by the government. Data were collected through interviews with 111 oil palm farmers, processed through normalization, and analyzed using the elbow method to identify the optimal number of clusters. The results identified three main clusters: low, medium, and high welfare levels. Land area and average monthly income were the most significant differentiating factors among the clusters. This study's fundamental distinction lies in applying the K-Means algorithm to integrate the socioeconomic aspects of oil palm farmers into specific clusters. These clusters will provide new insights into their welfare conditions. The findings are expected to assist governments and stakeholders in designing more effective and targeted development programs for oil palm