Variance-based importance measures for machine learning model interpretability - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Variance-based importance measures for machine learning model interpretability

Résumé

Machine learning algorithms benefit from an unprecedented boost in the industrial world, in particular in support of decision-making for critical systems. However, their lack of "interpretability" remains a challenge to leverage in order to make these tools fully intelligible and auditable. This paper aims to track and synthesize of a panel of interpretability metrics (called "importance measures") whose aim is to quantify the impact of each predictor on the statistical model's output variance. It is shown that the choice of a relevant metric has to be guided by proper constraints imposed by the data and the considered model (linear vs. nonlinear phenomenon of interest, input dimension, input dependency) together with taking the type of study the user wants to perform into consideration (detect influential variables, rank them, etc.). Finally, these metrics are estimated and analyzed on a public dataset so as to illustrate some of their theoretical and empirical properties.
Fichier principal
Vignette du fichier
1A - Variance-based importance measures for machine learning model interpretability.pdf (1.64 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03878431 , version 1 (29-11-2022)

Identifiants

  • HAL Id : hal-03878431 , version 1

Citer

Iooss Bertrand, Vincent Chabridon, Thouvenot Vincent. Variance-based importance measures for machine learning model interpretability. Congrès Lambda Mu 23 « Innovations et maîtrise des risques pour un avenir durable » - 23e Congrès de Maîtrise des Risques et de Sûreté de Fonctionnement, Institut pour la Maîtrise des Risques, Oct 2022, Paris Saclay, France. ⟨hal-03878431⟩
53 Consultations
67 Téléchargements

Partager

Gmail Facebook X LinkedIn More