IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661,p-ISSN: 2278-8727, Volume 17, Issue 1, Ver. III (Jan – Feb. 2015), PP 25-29 www.iosrjournals.org DOI: 10.9790/0661-17132529 www.iosrjournals.org 25 | Page Performance Analysis of Different Clustering Algorithm 1 Naresh Mathur, 2 Manish Tiwari, 3 Sarika Khandelwal 1 M.Tech Scholar, 2 Assistant Professor, 3 Associate Professor 1,2&3 Department of Computer Science Engineering, Geetanjali Institute of Technical Studies, Udaipur. Abstract: Clustering is the process of grouping objects into clusters such that the objects from the same clusters are similar and objects from different clusters are dissimilar. The relationship is often expressed as similarity or dissimilarity measurement and is calculated through distance function. some of the outlier detection techniques are distance based outlier detection distribution based outlier detection density based outlier detection and depth based outlier detection The goal of this paper is the detection of outliers with high accuracy and time efficiency. The methodology discussed here is able to save a large amount of time by selecting a small subset of suspicious transactions for manual inspection which includes most of the erroneous transactions. Keywords: PAM.CLARA, CLARANS, ECLARANS I. Introduction Data mining is the method of extracting patterns from data. It can be used to uncover patterns in data but is often carried out only on sample of data. analysis is a tool for exploring the structure of data. Cluster analysis is the organization of a collection of patterns (usually represented as a vector of measurements, or a point in a multidimensional space) into clusters based on similarity. Intuitively, patterns within a valid cluster Clustering is the process of grouping objects into clusters such that the objects from the same clusters are similar and objects from different clusters are dissimilar. The relationship is often expressed as similarity or dissimilarity measurement and is calculated through distance function. Clustering is useful technique for the discovery of data distribution and patterns in the underlying data. are more similar to each other than they are to a pattern belonging to a different cluster. Fig 1: Outlier Detection Module Outliers detection is an outstanding data mining task, referred to as outlier mining. Outliers are objects that do not comply with the general behavior of the data. By definition, outliers are rare occurrences and hence represent a small portion of the data. II. Categorization Of Clustering Techniques According to Data Mining concepts and Techniques by Jiawai Han and Micheline Kamber clustering algorithm partition the dataset into optimal number of clusters. They introduce a new cluster validation criterion based on the geometric property of data partition of the dataset in order to find the proper number of clusters. The algorithm works in two stages. The first stage of the algorithm creates optimal number of clusters , where as the second stage of the algorithm detect outliers. 2.1 Cluster Algorithms: Algorithms which are being used for outlier detection are-  PAM(Partitioning around Medoids)  CLARA(Clustering large applications)