On 08/12/2008 18:01, "Michael Thomas" <mike(_at_)mtcc(_dot_)com> wrote:
So, how do we factor in differential confidence levels in the final
I've often wondered whether you could do something with timing
the longevity of things in people's inboxes as first order
approximation of "value".
It's been done. Not sure if it proved more effective than spam/not-spam
Asrg mailing list