Survey of Different Data Clustering Algorithms
N. Kavithasri, R Porkodi · Zenodo (CERN European Organization for Nuclear Research) · 2018
Cluster is a group of objects that belongs to the same class. Clustering is widely used in diverse areas. There are number of clustering techniques available today. The financial data in banking and financial industry is generally reliable and of high quality which facilitates systematic data analysis and data mining. Data mining is mainly used in telecommunication industry used to identifying the telecommunication patterns, catch fraudulent activities, construct recovered use of source and obtain better value of service. This paper presents the study and analysis of five clustering algorithms namely Simple KMeans, Density Based clustering, Filtered Cluster, Farthest First, and Expectation Maximization for Individual household electric power consumption dataset. The performances of these algorithms are compared using the performance evaluation metrics namely Time taken to build, Number of cluster, and Number of cluster instances. The experimental results show that Filtered cluster, Simple KMeans and Farthest first produce better result than Expectation Maximization and Density Based.