- author = "Sean Stijven and Wouter Minnebo and Katya Vladislavleva",
- title = "Separating the wheat from the chaff: on feature selection and feature importance in regression random forests and symbolic regression",
- booktitle = "3rd symbolic regression and modeling workshop for GECCO 2011",
- year = "2011",
- editor = "Steven Gustafson and Ekaterina Vladislavleva",
- isbn13 = "978-1-4503-0690-4",
- keywords = "genetic algorithms, genetic programming",
- pages = "623--630",
- month = "12-16 " # jul,
- organisation = "SIGEVO",
- address = "Dublin, Ireland",
-
DOI = "
doi:10.1145/2001858.2002059",
- publisher = "ACM",
- publisher_address = "New York, NY, USA",
-
abstract = "Feature selection in high-dimensional data sets is an
open problem with no universal satisfactory method
available. In this paper we discuss the requirements
for such a method with respect to the various aspects
of feature importance and explore them using regression
random forests and symbolic regression. We study
'conventional' feature selection with both methods on
several test problems and a case study, compare the
results, and identify the conceptual differences in
generated feature importances.
We demonstrate that random forests might overlook important variables (significantly related to the response) for various reasons, while symbolic regression identifies all important variables if models of sufficient quality are found. We explain the results by the fact that variable importance obtained by these methods have different semantics.",
-
notes = "Also known as \cite{2002059} Distributed on CD-ROM at
GECCO-2011.
ACM Order Number 910112.",
