Call for Papers
Utility-Based Data Mining

A Special issue of the International Journal
Data Mining and Knowledge Discovery

Data Mining has made a profound impact on business practices and knowledge management in recent years. Business intelligence has emerged as one of the most popular applications of many data mining techniques. However, as our understanding of data mining improved, it became clear that in order to allow data mining to further its impact on business applications, it would be necessary to align the data mining process and algorithms with the broad economic objectives of the tasks supported by data mining.

All the different stages of the data mining process impact the ultimate economic utility derived from the data mining product. The economic utility of acquiring data, extracting a model, and applying the acquired knowledge must be considered. For example, in the data acquisition phase the costs of obtaining informative and accurate data may be considered to help identify the most cost-effective information. Similarly, economic utility also impacts the assessment of the decisions made based on the learned knowledge. Simple assessment measures like predictive accuracy have given way to economic measures, such as profitability and return on investment.

Utility-based data mining is a broad topic that covers all aspects of economic utility in data mining. As such, it encompasses the work in cost-sensitive learning and active learning as well as work on the detection of rare events of high utility value (e.g., anomaly detection).

This special issue will provide a leading forum for timely, in-depth presentation of recent advances in utility-based data mining. While economic utility considerations have played a much greater role in predictive data mining tasks, we also encourage papers on the use of economic utility in descriptive tasks.

We solicit high-quality, original papers describing work on the following non-exhaustive list of topics:

  • Cost-sensitive learning
  • Active learning and information acquisition for model induction
  • Pattern extraction algorithms which incorporate utility considerations
  • Interaction of economic/utility considerations between various steps in the data mining process (e.g., does misclassification cost affect what type of data should be purchased)
  • Types of economic factors (utility considerations) in data mining and their trade-off
  • Applications that take into account utility considerations

Submission Guidelines
Submission information can be found on the journal web page by clicking on "Instructions for Authors" on the sidebar. There are no specific page length restrictions. Authors should submit their manuscripts using DMKD's online system. To submit your article, go to the online manuscript submission page, select "submit a manuscript", create a user account, and, when prompted, choose "Special Issue: Util-Based Data Mining" as the article type. Please feel free to contact the guest editors with any questions.

Important Dates
Submission Deadline:    November 20, 2006
Expected Author Notification:    February, 2007
Expected submission of final manuscripts:    April, 2007

Special Issue Guest Editors
Gary M. Weiss, Fordham University,
Maytal Saar-Tsechansky, University of Texas at Austin,
Bianca Zadrozny, Instituto de Computaao, Universidade Federal Fluminense, Brazil,

Please note that the Second Workshop on Utility Based Data Mining will be held in conjunction with KDD-2006 in August 2006. We encourage authors to submit early versions of their journal submissions to this workshop.