You are viewing a plain text version of this content. The canonical link for it is here.

Posted to users@spamassassin.apache.org by Burton Windle <bw...@fint.org> on 2006/05/15 19:51:05 UTC

SA and Bayes in a multi-user environment

I currently use SA with Bayes filtering to filter my personal email, and 
it does an amazing job (zero false-negatives, very very few 
false-positives). I'd like to look into deploying SA in a coroprate 
enviroment as well; how well does Bayes handle email from 400 (or so) 
users as compared to just one? Would 400 people feeding it ham/spam email 
make it less accurate as a whole?


-- 
Burton Windle                           bwindle@fint.org

Re: SA and Bayes in a multi-user environment

Posted by Bart Schaefer <ba...@gmail.com>.

Bayes is only as accurate as its trainer(s).

http://www.jgc.org/blog/2006/05/theres-one-born-every-minute-spam-and.html