Arthur Zimek  (Ludwig-Maximilians-Universität )

Title: Ensembles for Outlier Detection

Abstract: In this talk, we discuss the recent topic of using ensemble techniques for outlier detection. To introduce the field, we will briefly sketch the data mining task of unsupervised outlier detection and discuss some basic considerations about ensemble techniques. Then we give an overview on the very few existing approaches to using ensemble techniques for outlier detection as well as on the challenges in doing so. In the main part, we discuss one of our recent contributions to this field, highlighting the issue of diversity of models in building effective ensembles. Finally, we will see some other examples of our recent research contributions. 

Host: Ira Assent