K-Means Clustering Analysis on the Distribution of Stunting Cases In Mojokerto Regency in June 2022

Abstract

The distribution of stunting cases in the Mojokerto regency is still not well mapped by the government, so the handling is not optimal. This stunting case needs attention from the government because it will also affect the development of an area or district. The method used by this study is the K-Means Clustering algorithm, where this study groups data into clusters based on the number of stunting cases that occur. This study clustered stunting case data in Mojokerto district to know the distribution of cases in each sub-district, sub-districts that have high levels of cases will get more handling or attention. Clustering can also show the likelihood of stunting in children varies significantly not only by individual child and household-level characteristics but also by provincial and sub-district level characteristics. The data used by this study is data on stunting cases in Mojokerto district in June 2022, which was obtained from the https://data.go.id website in the form of stunting case data in Mojokerto district in each sub-district based on gender. The results of clustering stunting cases using the K-Means algorithm are grouping regions based on the level of occurrence of cases into 3 clusters, namely cluster C1 (high), cluster C2 (medium), and cluster C3 (  low). Clustering in stunting cases in Mojokerto district using the K-Means algorithm has been successfully carried out, where the clustering resulted in 3 clusters. The K-Means Clustering method in this study produced 7 iterations so that the final results were obtained, namely 3  sub-districts entering cluster C1 (high), 14 sub-districts entering cluster  C2 (medium), and 10 sub-districts entering cluster C3 (  low). It is hoped that with the results of this clustering, the district government can be more optimal in handling stunting cases that occur.