Tutorial 2: Outlier Detection Techniques

Abstract:

This tutorial provides a comprehensive and comparative overview of a broad range of state-of-the-art algorithms for finding outliers in massive datasets. It sketches important applications of the introduced methods, and presents a taxonomy of existing approaches. In addition, relationships between the algorithmic approaches of each category of the taxonomy are discussed. Last but not least, at least one algorithm of each category is used for an empirical evaluation of the different approaches for outlier detection. The intended audience of this tutorial ranges from novice researchers to advanced experts as well as practitioners from any application domain where outlier detection methods are required.

Tutors' Biographies:

  • Hans-Peter Kriegel is a full professor for database systems and data mining in the Department Institute for Informatics at the Ludwig-Maximilians-Universitat Munchen, Germany and has served as the department chair or vice chair over the last years. His research interests are in spatial and multimedia database systems, particularly in query processing, performance issues, similarity search, high-dimensional indexing as well as in knowledge discovery and data mining. Hans-Peter Kriegel has been chairman and program committee member in many international database and data mining conferences. He has published over 200 refereed conference and journal papers, and he received the SIGMOD Best Paper Award 1997 and the DASFAA Best Paper Award 2006 together with members of his research team.

  • Peer Kroger holds a tenured position as Lecturer and Researcher (Akademischer Rat) at the database systems and data mining group of Hans-Peter Kriegel at the Ludwig-Maximilians-Universitat Munchen, Germany. He finished his PhD thesis on clustering moderate-to-high dimensional data in summer 2004 and his Habilitation in 2009. His research interests are in data mining and similarity search in high dimensional multimedia and biomedical data. Peer Kroger published more than 60 refereed conference and journal papers and he received the SDM Best Paper Honorable Mention Award 2008 together with his co-authors.

  • Arthur Zimek is a postdoc in the database systems and data mining group of Hans-Peter Kriegel at the Ludwig-Maximilians-Universit at Munchen, Germany. He finished his PhD thesis on correlation clustering in summer 2008. His research interests include data mining for high dimensional data and structured data especially for bioinformatics applications. Some of his recent publications include contributions to the tutorialís scope. Arthur Zimek received the SDM Best Paper Honorable Mention Award 2008 together with his co-authors and the SIGKDD Doctoral Dissertation Award Runner-Up 2009.