0 votes
in Python Flask by
What parameters are most important for tree-based learners?

1 Answer

0 votes
by

Some of the most common you could mention include:

max_depth - This is the maximum depth per tree. This adds complexity but at the benefit of boosting performance.

learning_rate - This determines step size at each iteration. A lower learning rate slows computation, but increases the chance of reaching a model closer to theoptimum.

n_estimators - This refers to the number of trees in an ensemble, or the number of boosting rounds.

subsample - This is the fraction of observations to be sampled for each tree.

Related questions

0 votes
asked May 9, 2023 in Python Flask by Robin
0 votes
asked Oct 16, 2021 in Petroleum Engineering by Robin
...