MENGUKUR KINERJA CLUSTERING MENGGUNAKAN ALGORITMA K-MEANS DAN K-MEDOIDS DENGAN OPTIMASI SILHOUETTE COEFFICIENT

AMELIA, KARINDA and Rini, Dian Palupi (2024) MENGUKUR KINERJA CLUSTERING MENGGUNAKAN ALGORITMA K-MEANS DAN K-MEDOIDS DENGAN OPTIMASI SILHOUETTE COEFFICIENT. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021282025054.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
	Text RAMA_55201_09021282025054_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_55201_09021282025054_0023027804_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB)
	Text RAMA_55201_09021282025054_0023027804_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (352kB) | Request a copy
	Text RAMA_55201_09021282025054_0023027804_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (391kB) | Request a copy
	Text RAMA_55201_09021282025054_0023027804_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021282025054_0023027804_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021282025054_0023027804_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (124kB) | Request a copy
	Text RAMA_55201_09021282025054_0023027804_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (142kB) | Request a copy
	Text RAMA_55201_09021282025054_0023027804_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (118kB) | Request a copy

Abstract

Clustering is one of the most widely used techniques in data processing that can be used to find patterns and characteristics in data. K-Means and K-Medoids are the most widely used clustering algorithms because they are simple, easy to implement, and relatively fast. Although proven to have good performance with high accuracy and efficiency for large data, previous studies have shown differences in clustering results between the two algorithms. Therefore, this study measures and compares the performance of K-Means and K-Medoids by applying Silhouette Coefficient optimization. Silhouette Coefficient is used to determine the optimal number of clusters based on the average silhouette value to optimize clustering performance. Tests were conducted by applying the K-Means, K-Medoids, and Silhouette Coefficient algorithms on three different datasets obtained from Kaggle in the range of 2 to 10 clusters. Evaluation of the clustering performance was done using Silhouette Score. The results show that the optimal number of clusters for all datasets is 2, both in the K-Means and K-Medoids algorithms. However, the K-Means algorithm shows better performance than K-Medoids with higher Silhouette Score values and close to 1. The highest Silhouette Score values of K-Means in the three datasets are 0.7099, 0.7674, and 0.7716, respectively. The K-Medoids are 0.7064, 0.7445, and 0.7257.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Clustering, K-Means, K-Medoids, Silhouette Coefficient, Silhouette Score
Subjects:	T Technology > T Technology (General) > T57-57.97 Applied mathematics. Quantitative methods
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Karinda Amelia
Date Deposited:	05 Jul 2024 05:43
Last Modified:	05 Jul 2024 05:43
URI:	http://repository.unsri.ac.id/id/eprint/149530

Actions (login required)

View Item