A Hierarchical Clustering Algorithm for Categorical Attributes

Clustering, an important technique of data mining, groups similar objects together and identifies the cluster number to which each object of the domain being studied belongs to. In this paper we propose a clustering algorithm which produces quite accurate clusters using the bottom up approach of hierarchical clustering technique of data with categorical attributes. A similarity measure has been proposed on the basis of which merge operations are carried out untill the desired number of clusters are obtained.