Clustering of Data on Vegetable Crop Production in the City of Bandung Using the K-Means Algorithm

Saputra, Ifano Rangga
Santoso, Cahyono Budy

Justek : Jurnal Sains Dan Teknologi
Vol 8, No 4 (2025): December

Vegetable farming supports urban food security, and Bandung City is one of West Java's main horticultural centers. However, vegetable production remains unevenly distributed across its sub-districts. This study analyzes production patterns from 2018–2023 using the K-Means Clustering algorithm. The dataset includes 12 major commodities, and the analysis involves data preprocessing, determining the optimal number of clusters using the Elbow Method and Silhouette Score, applying K-Means, and visualizing results through heatmaps and PCA. The findings reveal three clusters: Cluster 0 dominated by potatoes and the "others" category; Cluster 1 dominated by kale; and Cluster 2 dominated by shallots and petsai. These patterns indicate concentrated and specialized production across specific sub-districts. The study concludes that K-Means effectively identifies multi-commodity production similarities and provides strategic insight for Business Intelligence applications in agricultural planning and policy development.