The structure of the data set playing a vital role in datamining. In concept of datamining information recovery and pattern identification nothing but data clustering. There are multiple clustering algorithms have been commenced to clustering categorical data. Unfortunately these algorithms created an incomplete information. In recent times cluster ensembles have come out as an essential solution to overcome these limitations and to get the excellence results for clustering. A Link-Based similarity measure is proposed to guess unknown values from a link network of clusters and bridges the gap among the task of data clustering and that link examination. It also improves the ability of ensemble methodology for categorical data. A new Link-Based cluster ensemble approach is commenced which is well-organized than the previous model, where a binary cluster association matrix, like matrix is used to create the cluster ensembles. These cluster ensembles have impurity information, to overcome these problem Link-Based similarity algorithm is used to generate an accurate pure clusters.

Data clustering Cluster ensemble Link-based similarity measure Data sets.