>I agree, if all bayesian can do is get the last 1% then it is not
>worth the
 
>risk of a false positive. 

why that? the last 1% is the most difficult one and it may result in
hundreds of non detected spams. In our case 1% means 200 spammails/day.
actually when Bayesian filtering was invented, the guy who did it came
to the 99% barrier and realized he could not surpass it without
Bayesian. John Hanna made a great product out of this concentrating
solely on Bayesian. He realized (and wrote about) the limits of this
approach.

The new ASSP is meant to increase the quality of Bayesian by using
more and more example mails for fewer and fewer spam.



-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys - and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
_______________________________________________
Assp-user mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/assp-user

Reply via email to