From: matti.lyra@gmail.com   
      
   I've been involved in a machine learning project recently and am now   
   in the process of writing the project up for a paper submission. We   
   used the naive bayes classifier on the project and developed a method   
   for adjusting the classification of datapoints depending on how   
   exactly we want the classifier to perform, ie. increase or decrease   
   recall on one class in a binary classification problem. This is   
   similar to adjusting the classification threshold but is sensitive the   
   feature counts unlike just adjusting the classification threshold.   
      
   My question is if anyone knows of any previous research on methods   
   relating to adjusting the decision boundary in any other way than just   
   changing the classification threshold?   
      
   [ comp.ai is moderated ... your article may take a while to appear. ]   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)