Clustering Performance Comparison in K-Mean Clustering Variations: A Fraud Detection Study

Abstract

K-means clustering is a common clustering approach that is based on data partitioning. However, the k-means clustering has significant drawbacks, such as it is sensitive to deciding the initial condition. Several ways to improve the algorithm have been offered. To assess the algorithm's efficiency and correctness, the performance comparison should be evaluated. In this paper, several k-means algorithms, including random k-means, global k-means, and fast global k-means, were evaluated for their efficiency when applied to a fraud detection data set. The accuracy of each method and the Davies-Bouldin index was investigated for each algorithm to compare the clustering performance. The findings demonstrated that when a small number of groups was used, random k-means, global k-means, and fast global k-means gave similar clustering, but fast global k-means offered better errors when a big number of groups was used. Furthermore, global k-means took longer to execute than others.