Tuesday December 10, 2020 – 12:15-13:45pm – online
Agent-based ordinal classification for group decision making
Ons Nefla, Dauphine Univeristy
Abstract: In this research, we are interested in group decision aiding for ordinal classification problems. Our approach is based on a multiagent system where each decision maker is represented by a user agent and the decision process is guided by a mediator agent. Each user agent has a personalized preference- based behavior defined by a utility function. The aim of the process is to converge to a group classification using an automated negotiation procedure. Experiments with real and simulated data are presented in order to illustrate our approach and to learn about its performance on the decision makers’ welfare and privacy. Our approach is compared to two centralized methods (median and plurality).
Ons is PhD student in LAMSADE, the lab of decision making and data science at university of Dauphine. She has a degree in computer science from the Higher Institute of Applied Science and Technology in Tunisia, master degree in operational research at the University of Lorraine. She is currently validating a thesis at the University of Paris dauphine in co-direction with emlyon business school under the supervision of Pr. Meltem Öztürk and Dr. Imène Brigui-Chtioui on multi-agent approach for automated elicitation of preferences.