Using a random forrest implementation that does not support out-of-bag errors in combination with a bayesian hyper-parameter method, I am creating random validation datasets during the search. As pruning method I use a minimal number of observations per leaf.

After retrieving the optimal parameters, does this setup allow for a refit of the random forest on all the data?


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.