This paper discusses about various clustering techniques. It also describes about various pros and cons of these techniques. This paper also focuses on comparative analysis of various clustering techniques. | ISSN:2249-5789 Preeti Baser et al , International Journal of Computer Science & Communication Networks,Vol 3(4),271-275 A Comparative Analysis of Various Clustering Techniques used for Very Large Datasets Preeti Baser, Assistant Professor, SJPIBMCA, Gandhinagar, Gujarat, India – 382 007 Research Scholar, R. K. University, Rajkot [Email ID: priti_dalal007@] Dr. Jatinderkumar R. Saini, Director (I/C) & Associate Professor, Narmada College of Computer Application, Bharuch, Gujarat, India – 392 011. Research Guide, R. K. University, Rajkot [Email ID: saini_expert@] Abstract Data Mining is the process of extracting hidden knowledge, useful trends and pattern from large databases which is used in organization for decisionmaking purpose. There are various data mining techniques like clustering, classification, prediction, outlier analysis and association rule mining. Clustering plays an important role in data mining process. This paper focuses about clustering are several applications where clustering technique is used. Clustering is the process of assigning data sets into different groups so that data sets in same group having similar behavior as compared to data sets in other groups. This paper discusses about various clustering techniques. It also describes about various pros and cons of these techniques. This paper also focuses on comparative analysis of various clustering techniques. group and between groups gives best clustering result for data mining. The main objective of cluster analysis is to increase intra-group similarity and inter-group clustering techniques are widely used in variety of applications likecustomer groups for marketing, health support groups, planning a political strategy, locations for a business chain, hobby groups, student groups[19].Clustering also plays an important rolein an outlier analysis. Outlier detection is mostly used in fraud detection, intrusion detection[15]. Outlier is .
