XPost: comp.ai.neural-nets   
   From: kheor_@hotmail.com   
      
   First, you can see that problem as a time serie problem. Consequently,   
   you can use Neural network.   
   Second, it's in my opinion always a good idea to transform your   
   variable before do Neural Network. In that way, you take advantage of   
   you knoweldge and you put it on the data set.However, you must not   
   forget the transformation that you did if you want apply you NN on   
   generalization, or prediction set. For exemple, it's more easy to   
   estimate a time serie without trend and season ....   
      
   [ comp.ai is moderated.  To submit, just post and be patient, or if ]   
   [ that fails mail your article to , and ]   
   [ ask your news administrator to fix the problems with your system. ]   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)