Random forests variable importances Towards a better understanding and large-scale feature selection
Year: 2016
Type: conference-paper
Abstract: Good classification method with useful properties: Universal approximation Robustness to outliers Robustness to irrelevant variables (to some extent) Invariance to scaling of inputs Good computational efficiency and scalability Very good accuracy Loss of interpretability w.r.t.standard trees ⇒ but some interpretability can be retrieved through variable importance scores
Source: ORBi (University of Liège)
Author: Antonio Sutera
Institution: University of Liège
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3028982928