Comparison of K-Means Clustering Method with Hierarchical Clustering in Senior High School Clustering (SMA) in Surakarta

Fidi Febriani (Institut Teknologi Bisnis AAS Indonesia)
Amelia Shinta Dewi (Institut Teknologi Bisnis AAS Indonesia)
Muqorobin Muqorobin (Institut Teknologi Bisnis AAS Indonesia)

Proceeding of The International Conference on Electrical Engineering and Informatics
Vol. 1 No. 2 (2024): July : Proceeding of the International Conference on Electrical Engineering and

Clustering is one of the methods in data mining used in grouping data based on certain characteristics. This study aims to compare the performance of the K-Means Clustering and Hierarchical Clustering methods in clustering Senior High Schools (SMA) in Surakarta based on the parameters of the number of students, facilities, accreditation scores, and school achievements. In this study, a comparison was made between two popular clustering methods, namely K-Means Clustering and Hierarchical Clustering, to group Senior High Schools (SMA) in Surakarta City based on various relevant attributes. The attributes used include graduation rates, number of students, teaching quality, and available facilities. The results of the study show that both methods have their own advantages and disadvantages. K-Means is more efficient in terms of processing time, while Hierarchical Clustering provides a deeper understanding of the structure of relationships between SMAs. K-Means clustering provides better clustering results in terms of separation between clusters, with a higher Silhouette Score (0.52) and a lower Davies-Bouldin Index (0.88). This shows that K-Means is more efficient and better in clustering SMA based on the given data.