> well this ASSP has been in production for  1305 days
> 
> Spam Weight:    1,747,324
> Not-Spam Weight:   4,836,427
> 
> Corpus norm: 0.3613  (warning: ham heavy) 
> Corpus correction settings - low:"0.5 
> high:1.5 minimum files:10000 minimum 
> days:14"

It also depends from HOW you built your corpus,
see, if you used 3rd party emails to speed up things
then you probably got a spamdb which is NOT
matching your real life traffic... see, there is NO
"silver bullet", you HAVE to build up your own
spam corpus and ASSP needs to see *all* the
traffic, both inbound and outbound, set bayes to
"monitor" and let it work, when you'll have your
corpus ok you may switch your bayes filter to 
"score" so that it will have a "weight" on the 
spam filtering


------------------------------------------------------------------------------
This SF.net Dev2Dev email is sponsored by:

Show off your parallel programming skills.
Enter the Intel(R) Threading Challenge 2010.
http://p.sf.net/sfu/intel-thread-sfd
_______________________________________________
Assp-user mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/assp-user

Reply via email to