Courses

Previous | item10 | Next

			    KDD-2000:
	  The Sixth ACM SIGKDD International Conference
	     on Knowledge Discovery and Data Mining
http://www.acm.org/sigkdd/kdd2000

	       August 20-23, 2000, Boston, MA, USA

                          Tutorials
                     Sunday, August 20, 2000
http://www.acm.org/sigkdd/kdd2000/KDD2000-Tutorials.htm

                    KDD-2000 Tutorials Chair:
Raymond Ng (rng@cs.ubc.ca)
                  University of British Columbia

KDD-2000 will present six high quality Tutorials stimulating
synergy among the different subcommunities in data mining, i.e.
databases, machine learning, statistics, etc.  The tutorial
program provides an intensive and inexpensive training
opportunity to participants from industry and government. The
timeliness of the proposed topics make them of value to academic
researchers as well.

Attendance at KDD-2000 Tutorials is included with KDD-2000
registration (for more information on KDD registration fees and
the associated deadlines, please visit the conference web site
listed above).  Attendees will be asked to choose one morning
tutorial and one afternoon tutorial when registering for the
conference.  Tutorials will occur on Sunday, August 20, 2000.

Accepted KDD-2000 Tutorials are listed below with brief abstracts.
Please visit the following website for more detailed information:

http://www.acm.org/sigkdd/kdd2000/KDD2000-Tutorials.htm


KDD-2000 Morning Tutorials on August 20, 2000:

   M1. Data Mining for Hypertext
       Organizer: Soumen Chakrabarti (IIT Bombay)
       Abstract: With over 800 million pages covering most areas of
                 human endeavor, the WWW is a fertile ground for
                 data mining research to make a difference in the
                 effectiveness of information search.  We survey
                 recent advances in learning and mining problems
                 related to hypertext and the web.

   M2. Multidimensional Visualization for High Dimensional
       Datasets and Multivariate Relations
       Organizer: Alfred Inselberg (Tel Aviv University)
       Abstract: With emphasis being on the visualization of high
                 dimensional data, we focus on Parallel Coordinates.
                 The mathematical foundations for the display and
                 discovery of multidimensional relations without loss
                 of information are interlaced with a variety of
                 applications.

   M3. Knowledge Discovery in Biological Domains
       Organizers: I. Jurisica (University of Toronto)
                   I. Rigoutsos (IBM T.J. Watson Research)
                   A. Floratos (IBM T.J. Watson Research)
       Abstract: Biological research is generating data at an explo-
                 sive rate (e.g. the Human Genome Project).  This
                 tutorial introduces the latest computational tech-
                 niques for alphanumeric, visual and relational
                 biological data.

KDD-2000 Afternoon Tutorials on August 20, 2000:

   A1. Data Mining for Successful Customer Relationship Management (CRM)
       Organizers: Gregory Piatesky-Shapiro, Steve Gallant, Dorian Pyle
		   (Xchange)
       Abstract: Customer Relationship Management (CRM) is a broad,
                 holistic approach to doing business.  Successful
                 data mining in a CRM environment is far more than
                 the application of algorithms to data.  The tutorial
                 focuses on leveraging data mining concepts,
                 practices and procedures to get the most out of
                 them, and extend the miner's skill set within CRM.

   A2. Time Series Similarity Measures
       Organizers: Gautam Das (Microsoft Research),
                   Dimitrios Gunopulos (University of California -
                       Riverside)
       Abstract: Time series data account for a large fraction of
                 of the data stored in commercial databases.  A
                 fundamental problem of interest is to determine
                 whether 2 time series displlay similar behavior.
                 We describe the state-of-art of this area by comp-
                 aring and summarizing several of techniques in
                 detail.

   A3. High Performance Data Mining
       Organizers: Vipin Kumar (University of Minnesota)
                   Mohammed Zaki (Rensselaer Polytechnic Institute)
       Abstract:  Due to the huge size of data and amount of
                  computation involved in mining algorithms, parallel
                  and distributed processing is often considered an
                  essential component for a successful data mining
                  solution.  The goal of this tutorial is to provide
                  researchers, practitioners, etc. with an
                  introduction to high performance data mining.

Previous | item10 | Next