Clustering technique in data mining : general and research perspective.

Abstract

As the amount and dimensionality of data grows beyond the grasp of human minds, automation of pattern discovery becomes crucial. One of the most popular techniques to extract pattern and knowledge from large amount of data in databases is data mining. Data mining can be defined as process of searching the particular patterns and relationship from large amount of data in databases using sophisticated data analysis tools and techniques to build models that may be used to make valid predictions. One of the existing data mining techniques is clustering. Clustering in data mining is a discovery process that groups a set of data such that the intra-cluster similarity is maximized and inter-cluster similarity is minimizes. These discovered clusters are used to explain the characteristics of the data distribution. This paper present most popular clustering technique such as hierarchical clustering and partitional clustering, cluster selection schemes, clustering criterion functions, assessing cluster quality and conclusion.