CLUSTER ANALYSIS IN VIRTUALLY INTEGRATED ENVIRONMENTS

Today data clustering has been widely applied to many practical applications like social network analysis, scientific analysis. Since there is an enormous amount of data generated by the Internet users and because of limited memory, there is a need for the design of clustering algorithms. In this paper, we perform cluster analysis in virtually integrated environments. In cluster analysis, we apply BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies) algorithm on the dataset and perform global clustering and cluster refining to produce better clusters. This paper presents a way to implement BIRCH algorithm that is suitable for very large datasets and increase its efficiency by executing task in parallel. As a result, there is a linear growth of execution time with increase in dataset. The Information Technology (IT) industry is one among the most information and demanding industries. In the IT field, the finance department is the one where the knowledge and data keep on developing on a daily basis. It has been assessed that several companies are most affected by the inaccurate results produced by the softwares for calculating the financial data. Especially, the multi- national companies are mostly suffered due to the incorrect financial data available to them. The company has various branches all over the world. Each branch of the company has run different environments. One branch may have the network in the form of distributed environment and another branch may have the network in the form of cloud environment. Hence the data are heterogeneous in these different environments.