Classification of Mosque Typology Based on Distribution and Quantity Using K-Means Clustering in Indonesia

The objective of this study is to classify mosque typologies in Indonesia based on their quantity and spatial distribution using the K-Means Clustering algorithm. The dataset was obtained from the official website of the Ministry of Religious Affairs of the Republic of Indonesia and comprises the number of registered mosques across 34 provinces for the 2019–2023 period. The preprocessing procedures included data cleaning, provincial-level aggregation, and annual normalization to ensure consistency and comparability. The optimal number of clusters was determined through the Elbow Method, yielding three provincial categories (high, medium, and low) based on mosque density, referring to the total mosques recorded in each province. Centroid analysis revealed clear quantitative disparities among the clusters, while the spatial visualization showed a distinct geographical pattern in which western provinces such as West Java, Central Java, and East Java exhibited significantly higher mosque counts compared to eastern provinces such as Papua, Maluku, and East Nusa Tenggara. Collectively, these findings provide a rigorous, data-driven depiction of mosque distribution in Indonesia and offer a substantive foundation for advancing more equitable and sustainable religious infrastructure planning.