Roller Network is pleased to announce the addition of Bayesian filtering and learning to the SpamAssassin filter.
SpamAssassin offers optional Bayesian filtering and learning. By default, these options are disabled. The learning function and application of the filtering rules may be enabled or disabled independently. Using Bayesian classification, SpamAssassin is able to calculate a probability that a message is or is not spam. Our Bayesian database is distributed, allowing all of our mail servers learn and classify using a safe-queuing method to send updates to the master copy. Bayesian databases are unique to each mail domain.
For more information, see our SpamAssassin documentation at:
To enable Bayesian filtering and learning for your mail domain:
P.S. The addition of Bayesian classification was long overdue in our SpamAssassin offering. It took a while to design, test, and develop a system that would integrate into our existing load-balanced master/slave SQL cluster and unified account control center environment without modifying SpamAssassin. One of our design goals is to use unmodified versions of open source tools, rather than forking a closed-source version. If you have any questions about the bayes filter, please let us know.