Decision Tree Algorithm

Discussion in 'microsoft.public.sqlserver.datamining' started by anonymous_user, May 7, 2007.

  1. In the decision tree algorithm we can use 3 score methods (1) Entropy (3) Bayesian with K2 prior (4) Bayesian Dirichlet with Uniform prior for the tree nodes spilt. SQl Server 2005 Data Mining book does not give any infrmation about these methods. About Entropy I have a lot of information from the Internet, but for the other two the information I found can not make sense to me. If anyone knows exectly how Bayesian with K2 prior and Bayesian Dirichlet with Uniform prior works please help me. Thank you in advance.
     
    anonymous_user, May 7, 2007
    #1
    1. Advertisements

Ask a Question

Want to reply to this thread or ask your own question?

You'll need to choose a username for the site, which only take a couple of moments (here). After that, you can post your question and our members will help you out.