CRM114

[UxBoD]

> So, you didn't have to train it before use?

Nope, as we allowing the plugin to control the learning using what SA decided as being SPAM or HAM.  Though you can train it before hand using SPAM or HAM that you already have.

Regards,

--[ UxBoD ]--
// PGP Key: "curl -s https://www.splatnix.net/uxbod.asc | gpg --import"
// Fingerprint: C759 8F52 1D17 B3C5 5854  36BD 1FB1 B02F 5DB5 687B
// Keyserver: www.keyserver.net Key-ID: 0x5DB5687B
// Phone: +44 845 869 2749 SIP Phone: uxbod at sip.splatnix.net

----- Original Message -----
From: "Kai Schaetzl" <maillists at conactive.com>
To: mailscanner at lists.mailscanner.info
Sent: Monday, July 30, 2007 5:59:52 PM (GMT) Europe/London
Subject: Re: CRM114

UxBoD wrote on Mon, 30 Jul 2007 16:50:12 +0100 (BST):

> We raised our SA score from 5 too 12 as it was far to aggressive. The 7.36 score is > 
dynamically created by CRM based on the content within the CSS, so a HAM could (and I have > 
seen) have a score of -40.

Ah, I see. I was already wondering if it is applying scores based on weight as the 7.36
didn't look like something a human would put in.

> With respect to the training there is a option in the plugin that if SA scores a email as > 
either HAM/SPAM then the message will be learnt by CRM in the same manner. So in essence > 
they are truly working together.



Kai

-- 
Kai Schätzl, Berlin, Germany
Get your web at Conactive Internet Services: http://www.conactive.com



-- 
MailScanner mailing list
mailscanner at lists.mailscanner.info
http://lists.mailscanner.info/mailman/listinfo/mailscanner

Before posting, read http://wiki.mailscanner.info/posting

Support MailScanner development - buy the book off the website! 

-- 
This message has been scanned for viruses and
dangerous content by MailScanner, and is
believed to be clean.



-- 
This message has been scanned for viruses and
dangerous content by MailScanner, and is
believed to be clean.