A Recommender system based on MultiCriteria Aggregation

Soumana Fomba (1, 2) , Pascale Zaraté (2, 3) , Marc Kilgour (4)

1 USTTB - Université des Sciences, des Techniques et des Technologies de Bamako
2 IRIT-ADRIA - Argumentation, Décision, Raisonnement, Incertitude et Apprentissage
3 UT Capitole - Université Toulouse Capitole
4 WLU - Wilfrid Laurier University

Recommender systems aim to support decision-makers by providing decision advice. We offer multi-criteria decision recommendations based on a performance matrix and a partial order on criteria submitted by the user. Our method is to aggregate performance measures over all criteria based on inferences about preferences from the decision-maker’s input. After reviewing some multicriteria aggregation operators, we present a recommender system that uses the Choquet integral of a fuzzy measure to determine a total ordering of the alternatives.

Mots clés: Recommender system; Choquet integral; MCDA

Domaines: Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]; Logique en informatique [cs.LO]; Informatique et langage [cs.CL]

Soumana Fomba, Pascale Zaraté, Marc Kilgour. A Recommender system based on MultiCriteria Aggregation. 2nd International Conference on Decision Support Systems TechnologY (ICDSST 2016) EWG-DSS - EURO Working Group on Decision Support Systems, May 2016, Plymouth, United Kingdom. pp. 1-7. ⟨hal-01517389⟩