Bayes: Worth it?

[Derek Winkler]

    [ The following text is in the "iso-8859-1" character set. ]
    [ Your display is set for the "US-ASCII" character set.  ]
    [ Some characters may be displayed incorrectly. ]

>
> I'm running MailScanner as a gateway between the world, an
> internal Exchange server _and_ an internal Domino server.  MS
> scans all mail to and from the Internet, as
> well as mail between the internal Exchange and Domino server.
>
> In this type of configuration, is it worth using bayes?  I'm
> confused as to how I would properly train bayes to be effective
> in this environment, so I haven't bothered trying it.  Does
> anyone have any opinions on how and if this would work?
>
> Christian
>

My own setup MailScanner/Sendmail -> Exchange and only scan incoming mail
from internet with MailScanner.

Everyone else seems to be pro-Bayes but I turned it off ages ago and have
never looked back.

I did so for a few reasons:

Performance - without Bayes I could process many more messages

Bayes learning - doing the training on 4 MX hosts all running MailScanner
was painful and since they all do their own autolearning they are never
consistent. Until there is a way of using a central database no thanks. A
central database may be possible now, haven't looked into it in awhile.

Upgrading - upgrades without Bayes are so much easier, no database format
changes to deal with

So for me, no it's not worth it, but I'm open to trying it again. I'd only
enable it again if I thought it could make a significant difference to the
number of false positives/negatives.


This email and any files transmitted with it are confidential and
proprietary to Algorithmics Incorporated and its affiliates
("Algorithmics").  If received in error, use is prohibited.  Please destroy,
and notify sender.  Sender does not waive confidentiality or privilege.
Internet communications cannot be guaranteed to be timely, secure, error or
virus-free.  Algorithmics does not accept liability for any errors or
omissions.  Any commitment intended to bind Algorithmics must be reduced to
writing and signed by an authorized signatory.

------------------------ MailScanner list ------------------------
To unsubscribe, email jiscmail at jiscmail.ac.uk with the words:
'leave mailscanner' in the body of the email.
Before posting, read the MAQ (http://www.mailscanner.biz/maq/) and
the archives (http://www.jiscmail.ac.uk/lists/mailscanner.html).

Support MailScanner development - buy the book off the website!