Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 5 No 3 (2021): Maret 2021

Implementasi Metode Agglomerative Hierarchical Clustering Pada Segmentasi Pelanggan Barbershop (Studi Kasus : RichDjoe Barbershop Malang)

Rhayhana Putri Justitia (Fakultas Ilmu Komputer, Universitas Brawijaya)
Nurul Hidayat (Fakultas Ilmu Komputer, Universitas Brawijaya)
Edy Santoso (Fakultas Ilmu Komputer, Universitas Brawijaya)



Article Info

Publish Date
05 Mar 2021

Abstract

Strategy is one of many thing that influence the success of a person in running a business. Implementing the right strategy is crucial so that the business runs as desired. One of the strategies that can be applied is Customer Relationship Management (CRM), namely by regulating segmentation and how to treat consumers. In conducting analysis, business actors must carefully consider each consumer with their respective habits when conducting transactions to be grouped into certain segments. It is not uncommon for consumers to be in a segment that does not match their characteristics due to errors in the analysis because it is done manually. Therefore, this study will apply the Agglomerative Hierarchical Clustering method to Barbershop customers in segmenting. In this study, using 489 customer data from RichDjoe Barbershops Malang which were taken from May to October 2020 in the form of the latest arrival date of each customer marked with an ID number, the number of arrivals of each ID during a certain period of time, how much money was spent by each customer, and the accumulation distance from the oldest to the most recent date each ID number. The Agglomerative Hierarchical Clustering method is known to have a good ability in grouping data by making a hierarchy gradually from data in the form of singleton / individual until all data are grouped. The distance measurement method uses Manhattan Distance with the distance parameters used are Single Linkage, Complete Linkage and Average Linkage. This study uses the Silhouette Coefficient in evaluating the test and produces the highest results from 489 data at the 391 cut point, with an average silhoette coefficient value of 0.968850698 on the single linkage parameter and the average linkage resulting in 8 clusters and silhouette coefficient for each data resulting in 376 of 399 the right data are in the group and the silhouette coeffcient of each cluster formed shows that 6 out of 8 clusters are formed correctly.

Copyrights © 2021






Journal Info

Abbrev

j-ptiik

Publisher

Subject

Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Description

Jurnal Pengembangan Teknlogi Informasi dan Ilmu Komputer (J-PTIIK) Universitas Brawijaya merupakan jurnal keilmuan dibidang komputer yang memuat tulisan ilmiah hasil dari penelitian mahasiswa-mahasiswa Fakultas Ilmu Komputer Universitas Brawijaya. Jurnal ini diharapkan dapat mengembangkan penelitian ...