Visual Data Mining

Dr. Mihael Ankerst and Prof. Daniel A. Keim
Boeing, Seattle; University of Constance, Germany


The areas data mining and information visualization offer various techniques which effectively complement one another supporting the discovery of patterns
in the data. Whereas traditional (algorithmic) techniques are analyzing the data automatically, information visualization techniques can leverage the data mining process from an orthogonal direction by providing a platform for understanding the data and generating hypotheses about the data based on human capabilities such as domain knowledge, perception, and creativity. To successfully apply data mining algo-rithms, visualization and interaction capabilities become crucial factors since they enable the user to incorporate domain knowledge, to steer the data mining process and to better understand the results. In the past few years, novel visualization techniques have been specifically designed to support human involvement in the data mining process.

The goal of the tutorial is to provide an overview of visualization and interaction techniques that directly address specific data mining tasks. The tutorial presents the state-of-the-art in visual data mining, covering research prototypes as well as commercial systems. Visual support for the classic data mining methods such as association rules, clustering, classification and text mining are presented. To achieve an even more powerful combination of an algorithm and its visual support, both the mining algorithm and the visualization technique have to be designed under consideration of each other. The benefits of tightly integrating visualizations with mining algorithms is discussed and the first existing prototypes are described. The tutorial concludes with a summary and points out potential future directions.


MIHAEL ANKERST is working in the areas data mining, information visualization and database systems. He leads the design and development of the interactive, scalable data mining tools which tightly integrate data mining algorithms with visualization capabilities. He has published research papers for several conferences, including KDD 2001, 2000, '99, SIGMOD '99, InfoVis '98, Visualization '96, and Visualization '95, and in journals, including TKDE '98 and Informatica '99. He has served on program committees or as external referee for KDD '99, 2001 and 2002, InfoVis'99, The Computer Journal, TKDE and VLDB. He gave invited talks on human involvement in the KDD process at the LANL, AT&T, Simon Fraser University, University of Alberta and co-presented tutorials about "Visual Data Mining" at the PKDD'01 and KDD 2002. At KDD 2002, he also organized the panel: "The perfect data mining tool: interactive or automated?". He received his Ph.D. in 2000 at the University of Munich with a Ph.D. thesis on Visual Data Mining. Currently, he is employed by The Boeing Company being a member of the Data and Text Mining Group.

DANIEL A. KEIM is working in the area of information visualization and data mining, as well as similarity search and indexing in multimedia databases. In the field of
information visualization, he developed several novel techniques which use visualization technology for the purpose of exploring large databases. He was the chief engineer in designing the VisDB system - a visual database exploration system foccusing on pixel-oriented visualization techniques. He has published extensively on information visualization and data mining, he has given tutorials on related issues at several large conferences including SIGMOD, VLDB, KDD, and Visualization, he has been program co-chair of the IEEE Information Visualization Symposia 1999 and 2000, and program co-chair of KDD in 2002. He received his diploma (equivalent to an MS degree) in Computer Science from the University of Dortmund in 1990 and his Ph.D. in Computer Science from the University of Munich in 1994. He was an associate professor at the Institute for Computer Science of the Martin-Luther-University Halle, Germany. He worked in the data visualiation and exploration group at AT&T Shannon Research Labs and is now full professor of Computer Science at the University of Constance.

Return to Program