At 2:07 PM -1000 4/2/03, Clifton Royston wrote:
The main merit to my mind of having one number is that it allows you
to make some meaningful comparisons of similar systems, where certain
factors are bounded or held constant in the comparison. In the case
you mention above, if the organization demands FP < 0.1%, and has to
choose between tuning a system to give them 0.02% FP and 16% FN, or
0.025% FP and 2% FN, dSpam might give them an idea which to prefer.
I agree with Vernon. One number doesn't cut it. Actually, there was
a very good talk at the MIT Spam Conference by Microsoft on this
subject, and I think they did a good job of providing a way of
evaluation systems. That would be worth a check.
Of course I also was very fond of Praed's evaluation metric. How
well does it deal with deliberate evasion? But that one is a little
hard to measure.
--
Kee Hinckley
http://www.messagefire.com/ Junk-Free Email Filtering
http://commons.somewhere.com/buzz/ Writings on Technology and Society
I'm not sure which upsets me more: that people are so unwilling to accept
responsibility for their own actions, or that they are so eager to regulate
everyone else's.
_______________________________________________
Asrg mailing list
Asrg(_at_)ietf(_dot_)org
https://www1.ietf.org/mailman/listinfo/asrg