[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Re: bayesian filter training question



Kjetil Kjernsmo wrote:
> Finally, I found that SA, in it's default 3.0-form was much too 
> conservative about the assigned scores, so I have a bunch of rules that 
> I have adjusted the score of. You'll get some experience about that in 
> time, I guess. Also note that SA 3.1 has been released upstream.

    I tackled this from a different route.  I watched what SA scored different
messages and adjusted the cut-offs for tag-and-deliver and reject.  I found 15
was entirely too high for an outright reject.  I've personally never seen ham
get close to the 5.0 tag-and-deliver cutoff so adjusted the outright reject
down from 15 to 7.5ish.

-- 
         Steve C. Lamb         | I'm your priest, I'm your shrink, I'm your
       PGP Key: 8B6E99C5       | main connection to the switchboard of souls.
-------------------------------+---------------------------------------------

Attachment: signature.asc
Description: OpenPGP digital signature


Reply to: