University of Tuzla
Data mining, as a powerful knowledge discovery tool, aims at modeling relation-ships and discovering hidden patterns in large databases. Among four typical data mining tasks, outlier detection is the closest to the initial motivation behind data mining than predictive modeling, cluster analysis and association analysis. Outlier detection has been a widely researched problem in several knowledge disciplines, including statistics, data mining and machine learning. It is also known as anomaly detection, deviation detection, novelty detection and exception mining in some literature.