<![CDATA[The majority of parents take into account their child's educational standing to some extent. The school's status, number of schools, number of teachers, number of students, and number of classrooms are crucial considerations for parents when selecting a school. The problem is that data regarding the classification of elementary schools in the city of Pangkalpinang is not yet available so that parents and related agencies do not yet know the status & classification of schools in their area. The utilisation of machine learning has been possible for analysing data from Pangkalpinang City School, owing to the advancements in data science technology. This study generates a categorization of school data using clusters of school status. The research used an unsupervised machine learning (ML) model called K-means clustering for classification purposes. The dataset containing 14 sub-district records in Pangkalpinang, utilised for the k-means clustering technique, was acquired from the official website of the Ministry of Education and Culture (https://dapo.kemdikbud.go.id/). The authenticity of the data was verified by the Pangkalpinang City Education and Culture Office. This research use data modelling to establish school standards and utilises an algorithm to assess the precision of school categorization according to its parameters. According to the cumulative Sillhoette scores obtained from the school status, Cluster 1 for 21.43% of the total, Cluster 2 for 28.25%, Cluster for 14.28%, Cluster 4 for 21.42%, and Cluster 5 for 14.29%. The cluster with the lowest attribute values, specifically cluster 2, exhibits the highest number of clusters as shown from the cumulative plot findings. The Pangkalpinang City Government can determine and categorise elementary-level schools by aggregating the number of resulting clusters, as the entity responsible for education and potential pupils. This encompasses measures such as expanding the number of primary schools in areas facing a scarcity of such institutions, augmenting the teaching workforce in schools that necessitate additional educators, accommodating more students in schools that have a need for smaller student-to-teacher ratios in specific regions, and enhancing classroom infrastructure in schools lacking adequate space for in-person instruction.]]>
