
Interactive Elicitation for a Majority Sorting Model with Maximum Margin optimization
Nefla, Ons; Ozturk, Meltem; Viappiani, Paolo; Brigui, Imene (2019), Interactive Elicitation for a Majority Sorting Model with Maximum Margin optimization, dans Pekeč, Saša; Venable, Kristen Brent, Algorithmic Decision Theory - 6th International Conference (ADT 2019), Springer : Cham, p. 141-157. 10.1007/978-3-030-31489-7_10
Voir/Ouvrir
Type
Communication / ConférenceDate
2019Titre du colloque
6th International Conference on Algorithmic Decision Theory (ADT 2019)Date du colloque
2019-10Ville du colloque
Durham, NCPays du colloque
United StatesTitre de l'ouvrage
Algorithmic Decision Theory - 6th International Conference (ADT 2019)Auteurs de l’ouvrage
Pekeč, Saša; Venable, Kristen BrentÉditeur
Springer
Ville d’édition
Cham
Isbn
978-3-030-31488-0
Nombre de pages
181Pages
141-157
Identifiant publication
Métadonnées
Afficher la notice complèteAuteur(s)
Nefla, OnsLaboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Ozturk, Meltem
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Viappiani, Paolo

Laboratoire d'Informatique de Paris 6 [LIP6]
Brigui, Imene
autre
Résumé (EN)
We consider the problem of eliciting a model for ordered classification. In particular, we consider Majority Rule Sorting (MR-sort), a popular model for multiple criteria decision analysis, based on pairwise comparisons between alternatives and idealized profiles representing the "limit" of each category. Our interactive elicitation protocol asks, at each step, the decision maker to classify an alternative; these assignments are used as training set for learning the model. Since we wish to limit the cognitive burden of elicitation, we aim at asking informative questions in order to find a good approximation of the optimal classification in a limited number of elicitation steps. We propose efficient strategies for computing the next question and show how its computation can be formulated as a linear program. We present experimental results showing the effectiveness of our approach.Mots-clés
preference elicitation; ordinal classification; incremental elicitation; MR-sort; simulationsPublications associées
Affichage des éléments liés par titre et auteur.
-
Nefla, Ons; Ozturk, Meltem; Viappiani, Paolo; Brigui-Chtioui, Imène; Raboun, Oussama (2020) Communication / Conférence
-
Nefla, Ons; Brigui, Imène; Viappiani, Paolo; Raboun, Oussama (2020) Communication / Conférence
-
Denat, Tom; Ozturk, Meltem (2017) Communication / Conférence
-
Nefla, Ons (2021-06-30) Thèse
-
Napolitano, Beatrice; Cailloux, Olivier; Viappiani, Paolo (2021) Communication / Conférence