An experimental study of the intrinsic stability of random forest variable importance measures.

Abstract excerpt

BACKGROUND: The stability of Variable Importance Measures (VIMs) based on random forest has recently received increased attention. Despite the extensive attention on traditional stability of data perturbations or parameter variations, few studies include influences coming from the intrinsic randomness in generating VIMs, i.e. bagging, randomization and permutation. To address these influences, in this paper we...

Topics

Share this publication in a Topic to start or enrich a Post.

• Share to Algorithms
• Share to Cluster Analysis
• Share to Computational Biology