CLASS-L Archives

September 2005


Options: Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
"Peter C. Bruce" <[log in to unmask]>
Reply To:
Classification, clustering, and phylogeny estimation
Wed, 21 Sep 2005 11:43:52 -0400
text/plain (43 lines)
Dr. Anthony Babinec, President of AB Analytics and previously Director of 
Advanced Products Marketing at SPSS, will present two online courses in 
data mining at, each running from October 7 – November 
4.  Participants can ask questions and exchange comments with Dr. Babinec 
via a private discussion board throughout the period.

1.  “Data Mining – Unsupervised Techniques” covers key unsupervised 
learning techniques used in data mining – association rules, principal 
components analysis, and clustering.  This is a hands-on course that 
includes an integration of supervised and unsupervised learning techniques.

2. “Rule Induction” course covers two main machine-learning approaches to 
generating, or “discovering,” useful rules that describe the data in large 
databases. Association learning (producing “association rules” – if you 
bought “x”, you may also like “y”) will be considered, looking at the 
industry standard method: APRIORI.   As noted above, this is an 
unsupervised technique.  The course also covers two decision tree methods – 
C4.5 and CHAID.  Both are supervised machine learning processes in which 
classification rules are generated from data in which the class of each 
record is known (fraud/not-fraud; purchaser/not-purchaser, etc.).  The 
rules can then be applied to similar data in which the class is not known.

There is some overlap in coverage between the two courses; #1 is broader 
and more attentive to the larger data mining context, #2 is deeper and pays 
greater attention to the algorithms.  A tuition discount of 50% is 
available for “Rule Induction” if you take both courses at the same time: 
use the coupon code “RULES” (or “RULESA” for academic pricing) when signing 
up online.

As with all online courses at, there are no set hours when 
you must be online, and you can interact with the instructor over a period 
of 4 weeks via a private discussion board.  We estimate you will need about 
10 hours per week.

For details and 

Peter Bruce
The leading provider of online professional development in statistics
[log in to unmask]