Random forest
Bagging
After training, predictions for unseen samples x' can be made by averaging the predictions from all the individual regression trees on x':
Random forests for high-dimensional data
The basic random forest procedure may not work well in situations where there are a large number of features but only a small proportion of these features are informative with respect to sample classification. This can be addressed by encouraging the procedure to focus mainly on features and trees that are informative. Some methods for accomplishing this are:
Disadvantages
Another limitation of random forests is that if features are linearly correlated with the target, random forest may not enhance the accuracy of the base learner. Likewise in problems with multiple categorical variables.
Reading List
Report Issue