Proceedings of the 2007 SIAM International Conference on Data Mining
We are pleased to welcome you to the Seventh SIAM International Conference
on Data Mining(SDM 2007) in Minneapolis, Minnesota. This year the conference received a record
number of papers (302, as compared to 242 last year). Each submitted paper was reviewed
initially by at least three members of the international program committee. Area chairs then
initiated discussion on papers with discrepant scores and subsequently provided their
recommendations to the program co-chairs, who then collated and refined these suggestions across
all areas. In the end, 36 papers were selected to appear as full papers, and 39 papers were
selected as short papers or posters. We believe that the hard work of all the authors,
reviewers, and area chairs has resulted in an excellent set of papers that will be valuable both
to researchers and practitioners in data mining for many years to come.
To reflect the growing stature of this conference and the quality of its program, in addition to the regular paper presentation tracks, this year will mark the introduction of the plenary poster spotlight track prior to the poster reception. Poster presenters will be given two minutes to advertise and articulate the problem their work attacks and the nature of the solution. We hope that these very quick presentations will give attendees a sense of the problems that are solved in the posters and encourage them to discuss the posters with their authors during the subsequent poster session.
In addition to the contributed elements of the program, we are honored to have four prominent keynote speakers—Corinna Cortes (Google), Jerome H. Friedman (Stanford University), Tom Mitchell (Carnegie Mellon University), and Ajay Royyuru (IBM Research)—for what will undoubtedly be thought-provoking and enjoyable talks. The program also features an invited session on statistical learning chaired by Joe Verducci. Cutting edge tutorials by experts from industry and academia on topics ranging from data analytics for marketing and decision support to mining time evolving data using tensors, and from dimensionality reduction for data mining to statistical approaches to mining data streams, are also featured. The program is rounded out by two exciting and focused workshops on Text Mining and Biomedical Informatics featuring cutting edge research work by practitioners in these specialized fields.
We would like to take this opportunity to thank all the program committee members and external reviewers for their help in the difficult task of reviewing and choosing papers for presentation and posters. We are especially grateful for the help of area chairs, Charu Aggarwal, Lise Getoor, Thomas Hofmann, George Karypis, Jian Pei, Myra Spiliopolou, Andrew Tomkins, Anthony Tung, Geoff Webb, and Mohammed Zaki, who handled the reviewing process with great care and insight.
We would also like to thank all the SIAM staff members who have contributed to this conference—-it is in large part through their efforts that things got done on time. We are also grateful to Chid Apte, David Skillicorn, and Vipin Kumar for offering guidance on various program related issues. We would also like to acknowledge and thank the expert and prompt help of Rich Gerber of softconf.com, whose conference management software (START) greatly facilitated our work.
Finally, last but not least, this conference would not be possible without the excellent papers and presentations represented in these proceedings. We thank all the authors for their participation in SDM 2007!
Once again, we welcome you to SDM 2007 and trust that you will enjoy the conference!
Srinivasan Parthasarathy and Bing Liu, Program Chairs