DM: RE: Genetic Algorithms

[Sarabjot S. Anand]

Ron,
I have recently been using a genetic algorithm/Nearest Neighbour 
hybrid algorithm for predicting survival of patients with colorectal 
cancer and the results have been very encouraging. The algorithm 
provided a better model than a backpropagation based neural network 
implementation as well as a regression tree induction algorithm we 
used in the study. The search space (that of attribute weights) in 
our case is multimodal and from what I have gathered about GAs these 
are the kinds of spaces where GAs are most effective, as they have 
less of a tendency to get stuck in local optima as opposed to 
hill-climbing techniques.
A fairly comprehensive GA related web site is:
http://www.shef.ac.uk/~gaipp/galinks.html
However, these are not necessarily Data Mining. The only people I am 
aware of that are working in Data Mining using GAs are Prof. Vic 
Rayward-Smith of Univ. of East Anglia and Quadstone Ltd. in Edinburgh.
Sarab

-----Original Message-----
From:   Ron Hartman [SMTP:ron.hartman@thinkinc.com]
Sent:   Tuesday, August 12, 1997 2:22 PM
To:     datamine-l@nautilus-sys.com
Subject:        DM: Genetic Algorithms

There's been a lot of "buzz" about using Genetic Algorithms in Data 
Mining Applications.

1.) Can anyone share their experiences using these techniques to 
solve business problems, especially in direct marketing applications?

2.) Are they ready for "Prime Time"?  (are there any significant 
risks?)

3.) What are good resources to further my knowledge?

Thanks,

Ron Hartman
Vice President
NetCube Corporation