IMPLEMENTASI METODE CLUSTERING UNTUK PEMETAAN WILAYAH PRODUKSI DAN EKSPOR KOPI DI INDONESIA

Coffee is one of the main agricultural commodities in Indonesia, but the distribution of production and export contribution is still uneven. This study aims to map the patterns of coffee production and export in Indonesia using clustering methods, namely K-Means and Hierarchical Agglomerative Clustering (AHC). The data used includes coffee production by province and regency (2015–2022), as well as coffee export data by destination country (2016–2023), obtained from BDSP and BPS. The system is developed in the form of an interactive website that allows users to upload datasets, select clustering methods, and view analysis results in the form of tables, graphs, and interactive maps. Clustering quality is evaluated using the Silhouette Score and Davies-Bouldin Index (DBI). The testing results show that the optimal number of clusters is two for all datasets, with the highest Silhouette score reaching 0.85 and the lowest DBI of 0.21, indicating good clustering quality. AHC is more effective in analyzing export and provincial-level production data, while K-Means performs better for regency-level data. This system is expected to provide insights into the distribution patterns of coffee production and exports and support decision-making in the agricultural sector, particularly for coffee commodities.