<![CDATA[The livestock sector is one of the strategic contributors to regional economic development in West Nusa Tenggara (NTB), Indonesia. However, the unequal distribution of livestock populations across districts and municipalities presents significant challenges for formulating equitable and data-driven livestock development policies. Therefore, an objective grouping of regions based on livestock population characteristics is required to support effective decision-making. This study aims to analyze the clustering of livestock populations in West Nusa Tenggara Province using the K-Means clustering algorithm as a data mining approach to support data-driven decision-making. The study utilizes secondary data on livestock populations consisting of large livestock, small livestock, and poultry collected from all districts and municipalities in West Nusa Tenggara during the 2015–2024 period. Prior to the clustering process, the dataset was preprocessed through data cleaning, normalization, and attribute selection to improve clustering performance. The K-Means algorithm was then implemented by iteratively calculating Euclidean distance until the cluster centroids converged. The experimental results successfully classified the livestock population into three clusters representing low, medium, and high population categories. The clustering results reveal considerable disparities in livestock population distribution among regions, indicating different development priorities and resource allocation needs. Furthermore, the proposed clustering model provides valuable information for supporting regional livestock planning, livestock assistance distribution, infrastructure development, and strategic policy formulation. From an Informatics perspective, this study demonstrates the applicability of K-Means clustering as an effective data mining technique for regional classification and highlights its potential integration into Decision Support Systems (DSS) to facilitate evidence-based policy making in the livestock sector.]]>
