what is Random forest?
Random forest is an ensemble learning method. It corrects for decision trees' habit of overfitting to their training set. random forest classifier creates a set of decision trees from randomly selected subset of training set, then average the result.
Prons and Cons
Prons
- can be used for both regression and classification tasks
- very handly, easy to use, the number of hyperparameters is not high.
- unlikely to overfit
Cons
- ineffective for real-time predictions if the number of trees is large.
网友评论