Bayesian filtering is widely acknowledged by I.T. experts as the best way to catch spam. A Bayesian filter uses a mathematical approach based on known spam and ham (valid e-mail). This gives it a tremendous advantage over other spam solutions that just check for keywords or rely on downloading signatures of known spam.

ICE Systems and our partner’s Bayesian filters use an advanced mathematical formula and a dataset that is ‘custom-created’ for you. The spam data is continuously updated by ICE Systems and our partners and is automatically downloaded, whereas the ham data is automatically collected from your own outbound mail. This means that the Bayesian filter is constantly learning new spam tricks, and spammers cannot circumvent the dataset used. This results in a 98+% spam detection rate, after the required two-week learning period.

The really neat thing about Bayesian filters is that they're capable of learning. For example, if an anti-spam program using Bayesian technology decided to block an e-mail because the filter perceived it as junk, but the user marked it as valid mail, the Bayesian filter then knows not to block that type of e-mail in the future. In short, Bayesian filtering has the following advantages:

• Looks at the whole spam message, not just keywords or known spam signatures
• Learns from your outbound mail (ham) and therefore greatly reduces false positives
• Adapts itself over time by learning about new spam and new valid mail
• Dataset is unique to your company, making it impossible to bypass
• Multilingual and international