Grouped variable importance with random forests and application to multivariate functional data analysis - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2014

Grouped variable importance with random forests and application to multivariate functional data analysis

Résumé

In this paper, we study the selection of grouped variables using the random forests algorithm. We first propose a new importance measure adapted for groups of variables. Theoretical insights of this criterion are given for additive regression models. The second contribution of this paper is an original method for selecting functional variables based on the grouped variable importance measure. Using a wavelet basis, we propose to regroup all of the wavelet coefficients for a given func-tional variable and use a wrapper selection algorithm with these groups. Various other groupings which take advantage of the frequency and time localisation of the wavelet basis are proposed. An extensive simulation study is performed to illustrate the use of the grouped importance measure in this context. The method is applied to a real life problem coming from aviation safety.
Fichier principal
Vignette du fichier
Group_variable_selection.pdf (524.1 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01084301 , version 1 (18-11-2014)
hal-01084301 , version 2 (09-04-2015)

Identifiants

  • HAL Id : hal-01084301 , version 1

Citer

Baptiste Gregorutti, Bertrand Michel, Philippe Saint-Pierre. Grouped variable importance with random forests and application to multivariate functional data analysis. 2014. ⟨hal-01084301v1⟩
370 Consultations
1460 Téléchargements

Partager

Gmail Facebook X LinkedIn More