International Journal of Advanced Research in Computer Science and Software Engineering (IJARCSSE)
Clustering is the unconfirmed categorization of patterns into groups. This groups are known as clusters. Group consists of objects that are very similar among themselves whereas less similar compared to objects of the other cluster. This paper provides a Review of the existing literature on clustering techniques for data mining. Typically, data mining is the process of non-trivial extraction of previously indefinite, potentially valuable and implicit information from data. Data clustering is nothing but the one of the technique for collecting similar data into groups. So, in this paper, four popular researched data clustering techniques are discussed-Hierarchical, Partitioning, Expectation-maximization and soft-computing clustering techniques. Again the authors have explained some essential clustering algorithm's applications.