Implementasi K-Means Clustering Ujian Nasional Sekolah Menengah Pertama di Indonesia Tahun 2018/2019

Abstract

Clustering is an activity that aims to group a data that has a similarity between one data with another data. K-Means clustering is a non-hierarchical data clustering method that attempts to partition existing data into one or more clusters / groups. In this study clustering was conducted using the K-Means algorithm using data on the achievements of the National Middle School National Examination in 2018 obtained from the official website of the Center for Education and Culture Assessment of the Ministry of Education and Culture of the Republic of Indonesia. The results of the cluster with the K-Means algorithm are obtained for cluster 1 there are 14 provinces, cluster 2 there are 5 provinces, and cluster 3 there are 15 provinces with cluster 1 level is a cluster with a high national test score, cluster 2 is a cluster with a low national test score and a cluster 3 is a cluster with moderate national examination scores. While the results of the evaluation of the K-Means algorithm with the number of clusters 3 produce an evaluation value of Connectivity 11,916, Dunn 0.246 and Silhouette 0.464.