When you get continual mistakes for a particular address, my experience suggests you accidentally marked an email from your friend as spam once upon a time. The simplest approach might be to clear the decks (figuratively speaking) and start training from scratch. Only train on mistakes and unsures, and it will converge to pretty high accuracy fairly quickly.
Skip On Dec 30, 2017 1:58 PM, "Allen" <a...@att.net> wrote: Hi all, Windows 10, 62 bit and outlook 2016, 32bit. Spambayes Usually works like a champ. I have a correspondent that is almost always flagged as junk suspect. I have repeatedly marked this email as not spam, but the problem continues. The email address looks like dro...@trident.net (the only thing I have changed is the 4 letters before 63. I even have outlook play a tone and change the color to red and another add-in that examines this address and moves it back into the inbox. Nothing helps. Any suggestions? Al _______________________________________________ SpamBayes@python.org https://mail.python.org/mailman/listinfo/spambayes Info/Unsubscribe: http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html
_______________________________________________ SpamBayes@python.org https://mail.python.org/mailman/listinfo/spambayes Info/Unsubscribe: http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html
