Variable Importance Using Decision Trees

89 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

All Models are Wrong, but Many are Useful: Learning a Variable’s Importance by Studying an Entire Class of Prediction Models Simultaneously (2018, methodology): “…use U-statistics to study predictions of ensemble models fit to subsamples, similar to the bootstrap aggregation used in RFs. Procedures related to “Mean Difference Impurity,” another VI measure derived for RFs, have been studied theoretically by Louppe et al. (2013); Kazemitabar et al. (2017).”
Model Agnostic Supervised Local Explanations (2018, methodology): “DStump [11] simpliﬁes this measure further by only considering the splits made on the root nodes of the trees.”
Explainable AI for Trees: From Local Explanations to Global Understanding (2019, methodology): “To compare feature selection power we reproduce the same simulated independent features setting as [31] (but with strong 3rd order interactions) and compare the mean SHAP value of the loss vs.”
All Models are Wrong but many are Useful: Variable Importance for Black-Box, Proprietary, or Misspecified Prediction Models, using Model Class Reliance (2018, methodology): “Procedures related to “Mean Difference Impurity,” another VI measure derived for RFs, have been studied theoretically by (Louppe et al., 2013; Kazemitabar et al., 2017).”