A Study of Various Clustering Algorithms on Retail Sales Data

Data mining is the process of extraction of Hidden knowledge from the databases. Clustering is one the important functionality of the data mining Clustering is an adaptive methodology in which objects are grouped together, based on the principle of optimizing the inside class similarity and minimizing the class-class similarity. Various clustering algorithms have been developed resulting in a better performance on datasets for clustering. The paper discusses the four major clustering algorithms: KMeans, Density based, Filtered, Farthest First clustering algorithm and comparing the performances of these principle clustering algorithms on the aspect of correctly class wise cluster building ability of algorithm .The results are tested on datasets of retail sales using WEKA interface and compute the correctly cluster building instances in proportion with incorrectly formed cluster. A comparison of these four algorithms is given on the basis of percentage of incorrectly classified instances.