Boruta -- a tool for finding significant attributes in information systems CRAN Task View: MachineLearning (http://CRAN.R-project.org/view=MachineLearning) Boruta is a feature selection algorithm based on a randomForest classifier. It selects the full set of all relevant attributes by comparing original attributes' importances with importance achievable at random estimated using their randomised copies. Software Depends: R (>= 2.0.0), randomForest Suggests: mlbench Miron B. Kursa <M.Kursa@icm.edu.pl> Algorithm by Witold R. Rudnicki <W.Rudnicki@icm.edu.pl>, R implementation by Miron B. Kursa <M.Kursa@icm.edu.pl>. GPL (>= 2) 2012-02-22 application/tgz http://CRAN.R-project.org/package=Boruta