<![CDATA[Stunting remains a major public health problem and poses a significant challenge to human resource development in Indonesia. Differences in stunting management performance across provinces indicate regional disparities that require systematic and data-driven analysis. This study aims to cluster provinces in Indonesia based on the 2022 Stunting Management Specific Index (IKPS) and to compare the performance of the K-Means and K-Medoids clustering algorithms. The study uses secondary data from the Central Statistics Agency (BPS), covering 34 provinces and ten indicators composing the IKPS. Clustering was conducted using K-Means and K-Medoids algorithms. The optimal number of clusters was determined using the Elbow Method, while clustering quality was evaluated using the Davies–Bouldin Index (DBI). The results show that the optimal number of clusters is k = 5. Furthermore, the K-Medoids algorithm produces better clustering quality, as indicated by a lower DBI value compared to the K-Means algorithm, reflecting more compact clusters and clearer separation between provinces. The clustering results reveal distinct provincial groupings with varying stunting management characteristics, ranging from provinces with relatively strong and stable performance to those facing greater challenges related to geographical constraints and limited access to health services. Overall, this study demonstrates that cluster analysis is effective for identifying regional patterns in stunting management and can support policymakers in formulating more targeted, province-based strategies to improve the effectiveness of stunting prevention and intervention programs in Indonesia.]]>
Copyrights © 2025
