You are here

Data Mining Using SAS Enterprise Miner

Randall Matignon
Publisher: 
John Wiley
Publication Date: 
2007
Number of Pages: 
564
Format: 
Paperback
Price: 
80.00
ISBN: 
978-0-470-14901-0
Category: 
Textbook
[Reviewed by
Ita Cirovic Donev
, on
12/26/2007
]

Data mining techniques have gained much importance in many fields, ranging from medical studies and biostatistics to finance and economics. The need for a versatile and reliable application has never been greater. Today there are many software providers in the market, and SAS holds quite a large market share. Along with the software, the SAS Institute also provides many well written and quite detailed user guides and online courses. However, there is still the need for a book that would explain the software even better.

This book is an attempt to do just that. It goes through the Enterprise Miner and describes every node in great detail. It is written in a style that resembles a help file rather than an authoritative text on data mining techniques in SAS Enterprise Miner . The author only explains the nodes and completely neglects the statistical theory behind them. There is a brief introduction to each node followed by the node's options and the details of each node's sub-option.

One of the major drawbacks is that the author explains the nodes in the old Miner (4.3) rather than the new one (5.2). This is strange, given that the book is published when the new Enterprise Miner 5.2 is already in use. This is a big drawback, as there is a big difference between the two versions.

Overall this is a very detailed user guide. It could easily be a replacement to the SAS courses. The book gives much better descriptions of the Enterprise Miner possibilities than the original help file or the SAS published guides. The book can be successfully used as a user guide but only if one is already familiar with the statistical concepts of data mining (as they are omitted here completely) and the software differences of the Enterprise Miner versions.


Ita Cirovic Donev is a PhD candidate at the University of Zagreb. She hold a Masters degree in statistics from Rice University. Her main research areas are in mathematical finance; more precisely, statistical mehods of credit and market risk. Apart from the academic work she does consulting work for financial institutions.

The table of contents is not available.