71 citations · 76 across the 4 of their papers we have counts for
Showing 2020 · stat.MLShow all
2 papers · 2 filters
stat.ML2020★ 71 cited
Unbiased variable importance for random forests
Markus Loecher
The default variable-importance measure in random Forests, Gini importance, has been shown to suffer from the bias of the underlying Gini-gain splitting criterion. While the altern…
stat.ML2020★ 3 cited
From unbiased MDI Feature Importance to Explainable AI for Trees
Markus Loecher
We attempt to give a unifying view of the various recent attempts to (i) improve the interpretability of tree-based models and (ii) debias the the default variable-importance measu…