Open AccessSegmentasi Pelanggan Berdasarkan Perilaku Penggunaan Kartu Kredit Menggunakan Metode K-Means Clustering
Author(s) -
Fatimah Defina Setiti Alhamdani,
Ananda Ayu Dianti,
Yufis Azhar
Publication year - 2021
Publication title -
jiska (jurnal informatika sunan kalijaga)
Language(s) - English
Resource type - Journals
eISSN - 2528-0074
pISSN - 2527-5836
DOI - 10.14421/jiska.2021.6.2.70-77
Subject(s) - credit card , cluster analysis , issuer , computer science , loan , payment , business , data mining , dbscan , finance , artificial intelligence , fuzzy clustering , cure data clustering algorithm
Credit card is one of the payment media owned by banks in conducting transactions. Credit card issuers provide benefits for banks with interest that must be paid. Credit card issuers also provide losses to banks that have agreed to pay not to pay their credit card bills. To request a loan from the bank, a cluster model is needed. This study, proposing a segmentation system in research using credit cards to determine marketing strategies using the K-Means Clustering method and conducting experiments using the 4 methods namely K-Means, Agglomerative Clustering, GMM, and DBSCAN. Clustering is done using 9000 active credit card user data at banks that have 18 characteristic features. The results of cluster quality accuracy obtained by using the K-Means method are 0.207014 with the number of clusters 3. Based on the results obtained by considering 4 of these methods, the best method for this case is K-Means.