Analyzing the Performance of Various Clustering Algorithms

Abstract

Clustering is one of the extensively used techniques in data mining to analyze a large dataset in order to discover useful and interesting patterns. It partitions a dataset into mutually disjoint groups of data in such a manner that the data points belonging to the same cluster are highly similar and those lying in different clusters are very dissimilar. Furthermore, among a large number of clustering algorithms, it becomes difficult for researchers to select a suitable clustering algorithm for their purpose. Keeping this in mind, this paper aims to perform a comparative analysis of various clustering algorithms such as k-means, expectation maximization, hierarchical clustering and make densitybased clustering with respect to different parameters such as time taken to build a model, use of different dataset, size of dataset, normalized and un-normalized data in order to find the suitability of one over other.