You are viewing a plain text version of this content. The canonical link for it is here.
Posted to users@spamassassin.apache.org by "Savoy, Jim" <sa...@uleth.ca> on 2010/07/06 18:52:09 UTC
Bayes balance restored
Hi all - about a year ago, I displayed the results of my corpus as:
331,840 nspam
2,218,218 nham
for a 6.68::1 ratio of ham-to-spam.
While everything seemed to be getting scored properly, someone suggested
that it is
safer to have it closer to a 1-to-1 ratio, and recommended I change the ham
threshold
from the default 0.1 to something like -3.0. I did this and monitored the
corpus
monthly for a year. Here we are one year later (16 months actually) and my
numbers
are now:
4,472,874 nspam
4,854,055 nham
for a 1.09::1 ratio. Excellent!
I have now lowered the nham threshold to -1.0.
- jim -
PS I also turned on auto-whitelisting, which had been off before that. Not
sure if that
helped it regain its balance as well.