John Andersen said: >On Wednesday 08 January 2003 01:22 pm, rODbegbie wrote: >> You could have the most perfectly designed hashing and trust algorithms in >> the world, but there'd still be false positives and negatives. > > With that outllok on the subject. > why are you on a spam filtering engine's mailing list? > > If you sincerly believe that an occasional false positive > is worse than a daily mailbox of spam you would just put up > with the spam
John -- First off, Rod didn't say that he'd prefer a mailbox full of spam, over 1 FP. Dunno where you got that. Rod's point is that "there'd still be false positives and negatives". This is true -- no classifier will ever be 100% perfect. EVER. Not even a human. Not even the person the mail is aimed at! Given that, the aim is to _maximise_ effective classification with _minimum_ wrong classifications. Razor "gets humans in the loop", which (theoretically) helps on the difficult spam where automatic classification is hard. --j. ------------------------------------------------------- This SF.NET email is sponsored by: SourceForge Enterprise Edition + IBM + LinuxWorld = Something 2 See! http://www.vasoftware.com _______________________________________________ Razor-users mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/razor-users
