> Without being fed data for individual users, Bayesian > filtering becomes > less effective (how much less effective depends on how > similar your users > are; a small business will see better server-wide results > than an ISP, for > example), and that is most likely just a limitation you would > need to accept. > -Scott
FYI, Spamassassin by default comes with a default Bayesian database that is used server-wide which will work out of the box for the "average" user, but obviously you are going to get less than perfect results. From there, you can drill things down to a domain-wide Bayesian database, where things get a bit more precise. From there, individual users are able to able to create their own internal Bayesian database. Obviously, the most accurate results come from the user tuning the system themselves, rather than relying upon domain-wide or server-wide databases. Since Imail's software isn't exactly open source, there's no real telling how it is designed, although I'm guessing that it is loosely based on the Bayesian theory. As a server-wide implementation it has limited usefulness though. It should probably only be trusted in a weighted system to detect the "most obvious" of spam. One thing to also keep in mind is that just feeding a Bayesian database with equal amounts of spam and ham is usually not adequate to get accurate results. Most spam is full of HTML and obfuscation that helps little with Bayesian filtering, which usually takes a look at individual word or character strings. Most ham is full of words, with little HTML. When "balancing" a Bayesian database, I try to make sure that there is about 1.5x as much spam as ham, to make up for the lack of actual words that the Bayesian filter can catalog. That's only a general rule though, and should be tweaked in actual use. I think that there is some type of Spamassassin plug-in for Windows, and know that it can be used in a front-end MTA Postfix box, like an Imgate machine. William Van Hefner Network Administrator Vantek Communications, Inc. To Unsubscribe: http://www.ipswitch.com/support/mailing-lists.html List Archive: http://www.mail-archive.com/imail_forum%40list.ipswitch.com/ Knowledge Base/FAQ: http://www.ipswitch.com/support/IMail/
