CUSTOMER SEGMENTATION ANALYSIS BASED ON CREDIT USING K-MEANS CLUSTERING

Authors

  • Nuril Ahsina universitas ibn khaldun bogor
  • Fety Fatimah
  • Fitria Rachmawati

DOI:

https://doi.org/10.33197/jitter.vol8.iss3.2022.883

Keywords:

Customer Segmentation, K-Means Clustering, Elbow Method, Data Mining

Abstract

In a step optimizing a company's financing process, analyzing customer segmentation to make financing offers are right on target is what the company needs. Customer segmentation often uses the K-means Clustering algorithm method to help the grouping process into several clusters to get the significant data visualization results. K-means clustering algorithm is a data mining technique that can divide the data in a set into several groups where the similarity of  data in one group is greater than with data in other groups. Determination of the best number of clusters are possible to do based on the elbow method. Based on the elbow method, 4 cluster is the best cluster of all possible clusters .The results of the k-means clustering process from 1000 existing data, obtained from cluster 1 with a total of 286 customers with a percentage of 28.6%, cluster 2 with a total of 130 customers with a percentage of 13%, cluster 3 with the largest number of 542 customers, with a percentage of 54.2%, and cluster 4 having the lowest number of distributions, namely 42 customers with a percentage of 4.2% of the total data.

Downloads

Download data is not yet available.

Published

2022-08-15

How to Cite

[1]
N. Ahsina, F. Fatimah, and F. Rachmawati, “CUSTOMER SEGMENTATION ANALYSIS BASED ON CREDIT USING K-MEANS CLUSTERING”, jitter, vol. 8, no. 3, Aug. 2022.

Issue

Section

Articles