Elementary education serves as the foundational stage in efforts to improve the overall quality of education in Indonesia. Identifying regions with the lowest levels of elementary education is essential for effectively targeting initiatives to enhance education quality. The K-Means clustering algorithm is employed to group regions based on specific indicators, such as the number of students, dropout rates, classrooms, teaching staff, school principals, and others. The objective of this method is to identify regions with the lowest levels of elementary education by pinpointing clusters of areas that require the most support and development. K-Means clustering operates by dividing data into several clusters based on the similarity of feature patterns. This process facilitates the identification of regional groups with varying priorities for support and development. The clustering analysis results reveal that from 39 datasets related to elementary education across various regions in Indonesia, three clusters were formed. Cluster 0 consists of 34 data points, Cluster 1 contains only 1 data point, and Cluster 2 comprises 4 data points.