Explaining Robust Additive Decision Models: Generation of Mixed Preference-Swaps by Using MILP - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Explaining Robust Additive Decision Models: Generation of Mixed Preference-Swaps by Using MILP

Résumé

In this paper, we are interested in the question of explanation in Multicriteria Decision Aiding (MCDA) in general, and the explanation of the robust additive model in particular. To this end, a previous work has laid the foundations for explaining the necessary preference relation through a sequence of preference swaps. We propose to extend this work by introducing the concept of "mixed explanation" where the computation of its components is done through the resolution of a Mixed-Integer Linear Program. With the help of several examples, we motivate the interest of such an extension and open a discussion toward several promising further questions.
Fichier principal
Vignette du fichier
DA2PL_2020-5.pdf (255.24 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03230519 , version 1 (20-05-2021)

Identifiants

  • HAL Id : hal-03230519 , version 1

Citer

Manuel Amoussou, Khaled Belahcene, Christophe Labreuche, Nicolas Maudet, Vincent Mousseau, et al.. Explaining Robust Additive Decision Models: Generation of Mixed Preference-Swaps by Using MILP. From Multiple Criteria Decision Aid to Preference Learning (DA2PL 2020), Nov 2020, Trento (virtual), Italy. ⟨hal-03230519⟩
56 Consultations
53 Téléchargements

Partager

Gmail Facebook X LinkedIn More