A Novel Method for Outlier Entity Detection in Email Communication Network (ECN)

Abstract

This paper is the extension of the paper stated in [1].In the extended paper, elaboration of outlier entities are discovered based on the behavioral dissimilarities. Fifteen different features were proposed for this process using a variant of Kth nearest neighborhood (KNN) algorithm. Outliers were the convicted email users in ENRON, US based company which were already been declared convicted. The results in the papers proved to be matched with the 80% of the convicted email users because few of the users were not detected due to the constraints of the algorithm. In top 19 outliers detection 3 convicted users were found out. It means 15% of the result was achieved in top 20 users. The bench marking is made with the existing convicted and declared email users. The proposed features proved to helpful in the detection of outliers in email communication network and can be further implemented for various other kind of communication networks.