🎉 🎉 RAPIDMINER 9.10 IS OUT!!! 🎉🎉

Download the latest version helping analytics teams accelerate time-to-value for streaming and IIOT use cases.


How to create one final decision tree

KatL18KatL18 Member Posts: 1 Newbie
edited November 22 in Help
I need to create on final decision tree based on 25 different decision trees but I am not sure how to do that. They need to be constructed in a sequential manner where we update the weights of the training examples based on the prediction and the error rate of the previous decision. Right now I have the random forest operator where I have 25 different decision trees but what is it that I used to create one final decision tree?

Thank you


  • BalazsBaranyBalazsBarany Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert Posts: 712   Unicorn

    The process you're describing is implemented in ensemble models like Bagging and Boosting, and in Gradient Boosted Trees.

    However, these create *separate* trees. I don't see how one decision tree would be able to express all the different trees adequately and I don't know an algorithm implementing this. 

Sign In or Register to comment.