Implementasi Algoritma K-Means Pada Nilai Mahasiswa

Abstract

The values obtained by each student will vary. This depends on the student's ability to absorb the lecture
material given. The more students there are, the more variety of values that are seen. These values will only
appear as meaningless numbers, if no in-depth analysis is carried out. However, when explained using the
data mining method, these values will be presented in new knowledge that has been hidden so far. The
purpose of this study is to divide student values into 3 (three) clusters based on their similarities. The
method used is the K-Means algorithm. The results of the study showed that Cluster 2 (two) has the most
members with 18 (eighteen), then cluster 1 (one) with 8 (eight) and cluster 3 (three) has the least, namely
2 (two) members. The distribution of cluster 2 data is more diverse because it has the most members, the
distribution of cluster 1 is slightly piled up at one point, while cluster 3 only has 2 (two) members and has
a fairly large distance.