Review on determining number of Cluster in K-Means Clustering

TLDR: Six different approaches to determine the right number of clusters in a dataset are explored, including k-means method, a simple and fast clustering technique that addresses the problem of cluster number selection by using a k-Means approach.

Abstract: Clustering is widely used in different field such as biology, psychology, and economics. The result of clustering varies as number of cluster parameter changes hence main challenge of cluster analysis is that the number of clusters or the number of model parameters is seldom known, and it must be determined before clustering. The several clustering algorithm has been proposed. Among them k-means method is a simple and fast clustering technique. We address the problem of cluster number selection by using a k-means approach We can ask end users to provide a number of clusters in advance, but it is not feasible end user requires domain knowledge of each data set. There are many methods available to estimate the number of clusters such as statistical indices, variance based method, Information Theoretic, goodness of fit method etc...The paper explores six different approaches to determine the right number of clusters in a dataset