bagging: Training many models, each on a random resample of the data, and averaging their answers. The averaging cancels out much of each model's random error.
early stopping: Stopping training once the validation score stops improving, and keeping the best version so far.
ensemble: Several models whose answers are combined, by voting or averaging. Together they usually beat any one of them.
gradient boosting: Adding small decision trees one at a time, each fixing the mistakes left by the ones before.
out-of-bag: The rows a tree in a random forest never saw because they were left out of its bootstrap sample. Scoring on them gives a free test.
random forest: Many decision trees trained on different samples, voting together.
Keep learning
More in plain English.
1286 terms in the glossary, each with the lesson that teaches it.