As a result, the bias of the forest increases slightly, but due to the averaging of less correlated trees, its variance decreases, resulting in an overall better model.Ensemble Learning to Improve Machine Learning Results2.4K11Vadim SmolyakovRaghav GoyalFollowAug 25, 2017 · 1 min readshouldn’t the bias of the forest decrease ?since, you are using a subset of features