|
Let me see if I understood you right.
You got 360 spams. Their filter detected
300 of those spams, or 83%, and let 17% though?
If that impresses you, take a look at one of the Bayesian filters.
There are several free ones and commercial ones.
Using Bayesian filtering, I get about a 98.6% detection rate,
so my filter would miss 5 out of 360 spams rather than 60.
So far I've had one false positive (out of roughly 20,000 emails).
That false positive was a hotmail using who wrote the message
in all caps, used a lot of cuss words, and wasn't talking about business.
(With bayesian filtering, the filter learns which words indicate
a legit email, so if they mentioned words that my legit emails
have in them, like "script", "security", or even
"GFY" the filter would factor that word in, suggesting that
it may be a legit email.
__________________
For historical display only. This information is not current:
support@bettercgi.com ICQ 7208627
Strongbox - The next generation in site security
Throttlebox - The next generation in bandwidth control
Clonebox - Backup and disaster recovery on steroids
|