RE: DM: Datamining tools ... black boxes...

Many users care about data mining algorithms because they understand that 
their domain knowledge when added to knowledge of how the algorithms work 
can lead to a sustained competitive advantage.  SAS enjoys a reputation for 
having excellent documentation--the fact that our many data mining 
customers are asking for more is evidence that many data mining users DO 
care about how the algorithms work and how potentially adjusting the "dials 
and knobs" will empower them to achieve greater success and higher returns 
on investment.

In addition, the demand for the many data mining courses we offer 
(introductory to advanced) has remained very high for the past few 
years--also evidence that users care about the algorithms and how to get 
the most from their data.  The more the user understands about the 
algorithms, the greater success s/he can achieve in addressing a wide array 
of problems and opportunities.

How data mining is deployed is really an organizational issue.  For simple 
problems, a black box may yield better results than guessing.  For complex 
problems where the stakes are high, it makes sense to take more than a 
black-box approach if you want to get the utmost from your data.  No 
lasting competitive advantage is achieved with a black box.

Anne H. Milley
Global Marketing Strategist, Data Mining
SAS Institute Inc.
Business Solutions Division
95 Glastonbury Blvd.
Glastonbury, CT 06033
Phone:  (860) 633-4119  Ext. 8714
Fax:  (860) 633-4064
http://www.sas.com/

The opinions expressed here are mine and not necessarily those of SAS 
Institute.

• Prev by Date: DM: PKDD-2000 Workshops and Symposia Program - CALL FOR PROPOSALS
• Next by Date: Re: DM: New Subscription Policy and Instructions for Unsubscribing
• Prev by thread: RE: DM: Datamining tools ... black boxes...
• Next by thread: DM: Search results -- online experiment
• Index(es):
  • Date
  • Thread