A Novel Cluster Based Algorithm for Outlier Detection

Nowadays an important issue as well as challenge in data mining is obviously is outlier detection. Outlier detection has been used in many areas such as Fraud detection, Intrusion detection, Health care, Fault detection, etc., where detection of outliers is based on the different characteristics of data or datasets. In this current age of ‘Information Technology’, large numbers of processes are obtainable in the domain of data mining to discover the outliers by successfully creating the clusters and after that detecting the outliers from these created clusters. In data mining, cluster methods are highly essential and have been applied from micro- to macro-applications. Basically clusters are a pool of similar data objects put together grounded on the attributes and district features they have. Specifically outlier detection is used to recognize and exclude inconsistency from the available data sets. In the presented work an algorithm has been suggested which is based on clustering approach to the given data sets. The proposed algorithm efficiently detects outliers inside the clusters by using clustering algorithm and weight based approach.