| SIGMOD'98 Workshop on Research Issues in Data Mining and Knowledge
Discovery
Seattle, Washington
|
| Data Mining and Knowledge Discovery has become an active area of research,
attracting people from several disciplines: database systems, AI, machine
learning, statistics, information retrieval, and data visualization. Data
mining products and toolkits are now commercially available, and serious
industrial applications are being developed. Several interdisciplinary
conferences on the topic of data mining are now held regularly.
The Workshop on Research Issues in Data Mining and Knowledge Discovery (DMKD) was started two years ago as a forum for database researchers to discuss issues related to data mining from large databases and data warehouses. The first two workshops were held in conjunction with SIGMOD/PODS 1996 and 1997, and were successful in attracting a large number of participants. These two workshops focused primarily on advances in data mining algorithms and techniques. These topics have now become standard fare in the programs of leading database conferences. Therefore, this year we chose to additionally emphasize research issues and experience in developing and deploying data mining systems, applications, and solutions. These informal Proceedings contain 13 papers that were accepted for presentation out of 32 submitted. In addition, the program includes two invited industry presentations, by R. Uthurusamy of General Motors R&D Center and Kamal Ali of IBM Global Business Intelligence Solutions, and a research roundtable session with participants from several industry and university research groups. We would like to thank all the authors and attendees for contributing
to the success of the workshop. Special thanks are due to the Program Committee,
consisting of Rakesh Agrawal, Pamela Drew, Usama Fayyad, Jiawei Han, and
Jeff Ullman. We also gratefully acknowledge the financial support
of Hewlett-Packard Laboratories.
Surajit Chaudhuri and Umeshwar Dayal
|
| Data Mining and Knowledge Discovery has become an active area of research,
attracting people from several disciplines: database systems, AI, machine
learning, statistics, information retrieval, and data visualization. Data
mining products and toolkits are now commercially available, and serious
industrial applications are being developed. There are several interdisciplinary
conferences on the topic of data mining. The Workshop on Research Issues
in Data Mining and Knowledge Discovery (DMKD) was started two years ago
as a forum for database researchers to discuss issues related to data mining
from large databases and data warehouses.
The first two workshops were held in conjunction with SIGMOD/PODS 1996 and 1997, and were successful in attracting a large number of participants. These two workshops focused primarily on advances in data mining algorithms and techniques. These topics have now become standard fare in the programs of leading database conferences. Therefore, we have chosen to emphasize a somewhat different theme for this year's workshop. Our objective is to bring together researchers and practitioners to discuss research issues and experience in developing and deploying data mining systems, applications, and solutions. |
| The workshop will be held the day following the SIGMOD /PODS'98 conference. We expect about half a day to be devoted to technical presentations based on accepted papers. The program will also include several invited speakers from industry who will share their experience in developing and deploying data mining technology, and there will be time to discuss issues related to building data mining systems. |
| Please submit an extended abstract of no more than 5 pages in Plain Text, Word97, or Postscript format. You will need to submit the abstract electronically as follows: (1) send an email message to surajitc@microsoft.com at least 3 days prior to the submission deadline with the title, authors and affiliation; you will receive a response with the file name you should use for electronic submission (2) ftp ftp.research.microsoft.com (3) cd incoming/datamine/dmkd98 (4) set binary mode (5) put filename |
Major topics of interest include but are not limited to:
Abstracts will be evaluated on their ability to spark interesting discussion
at the workshop. Specifically, contributions that emphasize applications
or experience in building or using data mining systems are strongly encouraged,
and incremental algorithmic contributions are discouraged.
|
| There is no separate registration for the workshop. It is included in the SIGMOD/PODS'98 registration. |
| Abstract Due: April 24, 1998
Notification of Acceptance: May 4, 1998 Workshop Date: June 5, 1998 |
| Surajit Chaudhuri, Microsoft Research (surajitc@microsoft.com)
Umesh Dayal, Hewlett-Packard Laboratories (dayal@hpl.hp.com) |
| Rakesh Agrawal, IBM Almaden Research Center
Pamela Drew, Boeing Usama M. Fayyad, Microsoft Research Jiawei Han, Simon Fraser University Jeff Ullman, Stanford University |
| Prabhu Ram, Boeing |
| ACIRD: An Intelligent Internet Information System Based on Data Mining
Scaling Clustering Algorithms to Large Databases Recent Experiences with Data Mining in Aviation Safety Issues for On-Line Analytical Mining of Data Warehouses Robust Fuzzy Clustering Methods to Support Web Mining Stock Movement Prediction And N-Dimensional Inter-Transaction Association Rules MIND: A Scalable Classifier in Relational Databases Active Disks For Large-Scale Data Mining Scalable Techniques for Mining Causal Structures Identifying Unusual Spatio-Temporal Trajectories from Surveillance Videos Data Mining for Loyalty Based Management Web Document Clustering Theoretical Foundations of Associations Rules
|