<![CDATA[The government has set an annual target to reduce stunting rates. To achieve this, the Health Department must implement well-targeted policies based on a prioritized approach, ensuring that interventions are comprehensive and coordinated for maximum effectiveness. This study aimed to cluster urban villages in Samarinda based on stunting data, including the number of cases, baby weight, and height, using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) model. The optimal model was selected by determining the highest silhouette score from various combinations of epsilon (ε) and MinPts values. The best results were obtained with ε = 0.95 and MinPts = 3, which produced a silhouette score of 0.432. The clustering process resulted in the formation of two primary groups, whereas four villages remained unclustered, exhibiting significant variations in the number of stunted babies. Additionally, spatial analysis revealed that stunting and malnutrition were more prevalent in densely populated urban areas, emphasizing health risks associated with population density. These findings not only provide a clearer understanding of the spatial distribution of stunting in Samarinda but also highlight the need for targeted, area-specific interventions. The insights gained from this study offer a valuable basis for prioritizing public health initiatives and developing data-driven policies to effectively address stunting in Samarinda.]]>
Copyrights © 2025
