On Saturday 10 January 2004 11:23 am, Richard Urwin wrote:

> > I have to question that.  I know it's better known, but I get far
> > better rates under POPFile than I did when I tried SA.  POPFile
> > functions typically at 99.87% accuracy.  I don't think you can better
> > that.
>
> That's a very impressive number, but I don't see what POPFile does that SA
> doesn't. You do need to train SA, and it doesn't start using Bayesian
> analysis until it's database has 200 messages in. I don't have any
> experience of how easy, hard or accurate this bit of SA is. I run it at
> work, but the setup precludes training the Bayesian bit.

I don't really rely on bayesian filters at all, I let the DNS blocklists do 
the power filtering and just let the body filters catch the stuff coming from 
brand new sources.  I don't have particular numbers but on average, I get 800 
spam mails per week through my system and of those, maybe 1 false negative 
hits the inbox.

-- 
Bryan Phinney
Software Test Engineer


Want to buy your Pack or Services from MandrakeSoft? 
Go to http://www.mandrakestore.com

Reply via email to