K-means clustering based on gower similarity coefficient: A comparative study

Clustering is one of the most important Data Mining tasks employed in knowledge extraction and to partition data sets into similar groups. We present in this paper k-means clustering algorithm with different metrics and similarity measures in particular Gower similarity coeffecient. We use external validity measures to compare the result of k-means using weka. The experiments are carried out for various data sets of VCI machine learning data repository. Experimental results show that the accuracy of k-means algorithm using Gower similarity coeffecient is better than the other tested metrics for the used data sets.