Feature Selection with the Boruta Package

By Miron Bartosz Kursa, Witold R. Rudnicki. 2010

4,947 citations recorded by the source corpus.

This article describes a R package Boruta, implementing a novel feature selection algorithm for finding emph{all relevant variables}. The algorithm is designed as a wrapper around a Random Forest classification algorithm. It iteratively removes the features which are proved by a statistical test to be less relevant than random probes. The Boruta package provides a convenient interface to the algorithm. The short description of the algorithm and examples of its application are presented.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ecc2ca3150dc4d4d8dceedab244114f191e05742

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Tumor Microenvironment Characterization in Gastric Cancer Identifies Prognostic and Immunotherapeutically Relevant Gene Signatures (2019, methodology): “Then, the random forest classification algorithm was used to perform dimension reduction in order to reduce noise or redundant genes (33).”
An extensive experimental survey of regression methods (2019, background): “input is removed when a statistical test proves that it is less relevant 1013 than a shadow random input, created by shuffling the original ones [55].”
Machine Learning and Integrative Analysis of Biomedical Big Data (2019, neutral): “Recursive feature elimination (RFE) [58], boruta [59], and jackstraw [60] are popular wrapper methods that repeatedly construct a model (e.”
VSURF: An R Package for Variable Selection Using Random Forests (2015, methodology): “Let us cite, for classiﬁcation problems the R package Boruta , described in Kursa and Rudnicki (2010), which aims at ﬁnding all relevant variables using a random forest classiﬁcation algorithm which iteratively removes the variables using a statistical test.”
Robustness of Random Forest-based gene selection methods (2013, methodology): “Both RF-ACE [6, 7] and Boruta [8] algorithms are based on the idea first introduced in [12] — they extend the information system with shadows, artificial attributes created by permuting the order of values in original ones and use their importance scores to judge the significance of the scores obtai”