Data stream mining gained in importance over the last years because it is indispensable for many real applications such as prediction and evolution of weather phenomena; security and anomaly detection in networks; evaluating satellite data; and mining health monitoring streams. Stream mining algorithms must take account of the unique properties of stream data: infinite data, temporal ordering, concept drifts and shifts, demand for scalability etc.

Learning on streams has followed two threads thus far: mining (classification, clustering, frequent itemset discovery) and probabilistic modeling. In both threads, scholars devise solutions to the above problems. Stream clustering algorithms are more oriented towards scalability and tracing of model changes, while dynamic probabilistic modeling, e.g. dynamic topic modeling, encompasses methods that adapt seamlessly to drifts. At the same time, research on unsupervised stream learning seems to be scattered along the many application areas. Examples of areas that seem to evolve independently are sensor mining, mining on clickstreams and other logs in stream form, topic modeling on document streams, and temporal mining on data that are actually streams. With this workshop, we attempt to bring together the advances on those complementary areas.

Suggested topics:

* Clustering and classification on streams
* Probabilistic modeling on dynamic data
* Frequent itemset discovery on streams
* Dealing with concept drift
* Change and novelty detection on streams
* Scalable stream mining algorithms
* Visual analytics on streams

We particularly solicit works for challenging application areas, such as:

* Security
* Assisted living
* Patient monitoring
* Traffic monitoring
* Recommendation engines
* Customer lifetime management

Keynote Speech
Speaker and topic: TBD

Important Dates

Submission date for full papers: May 4, 2010
Author notification: May 21, 2010
Submission of camera-ready paper: May 28, 2010
Half-day workshop at ACM SIGKDD conference: July 25, 2010 (afternoon)

Paper Submission

Submissions have to be 9 pages or less using the ACM template (http://www.acm.org/sigs/publications/proceedings-templates).

Electronic submission via http://www.easychair.org/conferences/?conf=streamkdd2010

Proceedings

All submitted papers will be refereed for quality and originality by the Program Committee. Accepted papers will be published in the workshop proceedings, which will be included in the ACM Digital Library.

The best paper and a workshop report will be published in KDD Explorations. We are currently working on an outlet to publish complete post-proceedings.

Organizers

Margaret H. Dunham
Intelligent Data Analysis Group (IDA)
Department of Computer Science and Engineering
Lyle School of Engineering
Southern Methodist University
Dallas, Texas 75275
U.S.A.
mhd [at] lyle.smu.edu

Michael Hahsler
Intelligent Data Analysis Group (IDA)
Department of Computer Science and Engineering
Lyle School of Engineering
Southern Methodist University
Dallas, Texas 75275
U.S.A.
mhahsler [at] lyle.smu.edu

Myra Spiliopoulou
Workgroup KMD: "Knowledge Management & Discovery"
Faculty of Computer Science
Otto-von-Guericke-Universität Magdeburg
PO Box 4120, D-39016 Magdeburg
Germany
myra [at] iti.cs.uni-magdeburg.de

Program Committee

* Sanjay Chawla, University of Sydney, Australia
* João Gama, Universidade do Porto, Portugal
* Le Gruenwald, NSF/University of Oklahoma, USA
* Eamonn Keogh, University of California - Riverside, USA
* Latifur Khan, University of Texas at Dallas, USA
* Chi-Hoon Lee, Yahoo! Labs, USA
* Mohammad Masud, University of Texas at Dallas, USA
* Tamer Özsu, University of Waterloo, Canada
* Spiros Papadimitriou, IBM T.J. Watson Research Center, USA
* Thomas Seidl, RWTH Aachen University, Germany
* Dimitris Tasoulis, Imperial College London, UK

Webmaster
Michael Hahsler (mhahsler [at] lyle.smu.edu)