What are Adaptive Filters
Adaptive filters learn from the environment as time passes by. This learning ability improves the junk mail filtering functionality in Xeams.
There are two types of adaptive filters in Xeams
- Bayesian Analysis
- Auto-learn sender
Bayesian spam filters calculate the probability of a message being spam based on
its contents. Unlike simple content-based filters, Bayesian spam filtering learns from spam and from
good mail, resulting in a very robust, adapting and efficient anti-spam approach that, best of all,
returns hardly any false positives.
to learn more about
the Bayesian Filter
and tips on how to improve it
for your needs.
This filter is used when you use Xeams to handle out-bound emails. Xeams learns and remembers email
addresses on the Internet that receive emails from your local users. To understand this
filter, consider the following scenario.
- Mark, who is a user in your company sends an email to Mary who is a user on the Internet
- You have configured Xeams to accept out-bound messages
- Since Mark is a local user, Xeams will allow his message to go through and will also remember that Mark has sent an email to Mary.
- When Mary replies back to Mark, the system gives credit to Mary's message hence avoiding a false-positive
Scoring for Auto-Learn Sender
Considering the above example, Mary is going to get a credit of 25 points by default for every message generated
by Mark. For example, if Mark has sent 4 emails to Mary in the past, incoming messages from Mary will get a
Follow the steps below to change the default score of 25 to a higher/lower values.