Distributional Random Forests: Heterogeneity Adjustment and Multivariate Distributional Regression. (arXiv:2005.14458v3 [stat.ML] UPDATED)

Random Forest (Breiman, 2001) is a successful and widely used regression and
classification algorithm. Part of its appeal and reason for its versatility is
its (implicit) construction of a kernel-type weighting function on training
data, which can also be used for targets other than the original mean
estimation. We propose a novel forest construction for multivariate responses
based on their joint conditional distribution, independent of the estimation
target and the data model. It uses a new splitting criterion based on …

arxiv random random forests regression