Existing literatures that concerns using decision tree to do regression is more limited compared to its classification companion. The same also holds for research regarding active learning. I am just curious, if the following is a good or poor method for regression: we use decision tree as the regressor, and we are allowed to acquire more data samples, probably depend on some "uncertainty measure" of the decision tree, and hoping it would improve the model accuracy. Also is it possible for ensemble methods, like, using some query-by-bagging/boosting to do regression?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.