Application Of K-Means Clustering Algorithm Method In New Student Admissions

Abstract

In the admission process of Muhammadiyah Junior High School 6 which is done repeatedly every year and the data increases continuously, thus slowing down the search for information on existing data. This study aims to classify the new student admission data in SMP Muhammadiyah 6 using Clustering techniques. The algorithm used for cluster formation is k-Means algorithm. K-Means is one of the clustering methods that can group the data of new students who have very similar characteristics grouped in the same cluster. The implementation uses RapidMiner which is used to help find more accurate values. The attributes used are school origin and national test scores. To find out the number of clusters and items in the cluster Euclidean distance calculation of the data in the can, calculated from the distance of the first student data to the center of the first cluster is 0,then the distance of the first new student data to the second cluster is 2.2 and the distance of the first new student data to the third cluster is 1.4. The results of the research carried out formed three clusters, with the first cluster totaling 31 items, the second cluster totaling 37 items and the third cluster totaling 32 items. From the cluster that we can be used as one of the basic decision-making for students who are accepted and not accepted at SMP Muhammadiyah 6.