Hybrid Approaches for Outlier Detection and their Comparative Analysis

Data mining deals with the discovery of significant, hidden and interesting knowledge from large amounts of data. With the development of information technologies, the number of databases, as well as their dimension and complexity, grow rapidly, resulting in the necessity of automated analysis of great amount of heterogeneous structured information. Hence, the use of data mining systems came into existence. One of the biggest problems faced by the data mining systems today is to detect and remove the outliers. Outlier detection is one among the major issues in data mining systems. Outliers arise due to mechanical faults, changes in system behavior, fraudulent behavior, network intrusions or human errors. The paper discusses hybrid approaches for outlier detection methods used in data mining systems. Different algorithms of clustering and distance based methods are being discussed and experimented.