School zoning system using K-Means algorithm for high school students in Makassar City

Abstract

The process of admitting High School Students in Makassar City produces a lot of student data, in the form of student learning activities data and also student profile data. This affects the search for information on the data. This study discusses the grouping of students towards Makassar City Public High Schools by utilizing the data mining process using clustering techniques. The algorithm used for cluster formation is the K-Means algorithm. K-Means is a nonhierarchical data clustering method that can group school data into several clusters based on the similarity of the data. Euclidean Distance is used to determine the distance of school points and address points for students. The proposed system is a zoning area determination system for acceptance of high school students on a noncircle basis using student data and school data. The data used are 22 school data and 1547 student data. The results of this study are used as a basis for decision making to determine optimal school zoning so that student distribution is evenly distributed based on the cluster formed. The aim is so that the data distribution does not overlap for schools that are close together so that schools that have the closest distance are grouped in one cluster.