Implementasi Algoritma Klasterisasi K-Medoids untuk Segmentasi Pengguna E-Ujian.Com

Putra, Anggyi Trisnawan

J-SAKTI (Jurnal Sains Komputer dan Informatika)
Vol 6, No 2 (2022): EDISI SEPTEMBER

User behaviour management and analysis is very important in business. A good marketing strategy needs to be done so that the loyalty of old users is maintained. This can be initiated by segmenting users so that a good marketing strategy can be formulated. Customer segmentation can be done with the help of one of the data mining methods,  which is clustering. In this study, k-medoids algorithm is used to cluster e-ujian.com users based on the behavioral data of each user. The first step will be analyzing data attributes that can be used. Next, the clustering process was carried out with the experimentally determined value of k. Finally, the cluster results will be evaluated using the Davies Bouldin Index (DBI) to determine the best number of clusters. The results showed that the value of k = 4 became the optimal number of clusters with a DBI value of 3,017.