Penerapan metode k-means clustering untuk pengelompokan Kabupaten/Kota Jawa Timur berdasarkan karakteristik penyebab stunting

Stunting is a condition in which a child's height is shorter than the average measurement standard. In this case, stunting is a serious nutritional problem, including in East Java Province. This study aims to apply the K-Means clustering method in grouping districts/cities in East Java based on factors that cause stunting such as the prevalence of underweight toddlers, the prevalence of stunted toddlers, families at risk of stunting, proper drinking water sources, not having a proper toilet, and improper housing. From the evaluation of cluster validation using the K-Means algorithm with the silhouette index for the number of clusters ranging from K = 2 to K = 9, it was found that the most optimal number of clusters was 2 clusters, with a silhouette value of 0.3707 which showed good cluster separation quality in K2. Based on the evaluation of clustering results with the K-Means algorithm, two main clusters were obtained which were categorized as low stunting potential and high stunting potential areas. Kab. Malang, Kab. Lumajang, Kab. Jember, Kab. Banyuwangi, Kab. Bondowoso, Kab. Probolinggo, Kab. Pasuruan, Kab. Bangkalan, Kab. Sampang, Kab. Sumenep, Kab. Pamekasan, and Surabaya City as areas with high stunting potential. These findings are expected to be a reference in the formulation of more targeted stunting prevention policies in East Java Province.