A user-oriented implementation of the ELECTRE-TRI method integrating preference elicitation support

This paper presents a new implementation of an existing method called ELECTRE TRI, which integrates specific functionalities supporting the decision maker (DM) in the preference elicitation process and aims at reducing the cognitive effort required from the DM in the phase of calibration of the preference model.

Abstract

Multiple Criteria Sorting Problem consists in assigning a set of alternatives A={a1,a2,…,al} evaluated on n criteria g1,g2,…,gn to one of the categories which are pre-defined by some norms corresponding to vectors of scores on particular criteria, called profiles, either separating the categories or playing the role of central reference objects in the categories. The assignment of an alternative ak to a specific category results from a comparison of its evaluation on all criteria with the profiles defining the categories. This paper presents a new implementation of an existing method called ELECTRE TRI. It integrates specific functionalities supporting the decision maker (DM) in the preference elicitation process. These functionalities grouped in ELECTRE TRI Assistant aim at reducing the cognitive effort required from the DM in the phase of calibration of the preference model. The main characteristic feature of ELECTRE TRI Assistant is the inference of the ELECTRE TRI preferential parameters from assignment examples supplied by the DM. The software is presented through an illustrative example. Decision makers (DMs) often face decision situations in which different conflicting viewpoints (goals or criteria) are to be considered. The field of multiple criteria decision aid (MCDA) offers the DMs a selection of methods and operational tools that explicitly account for the diversity of the viewpoints considered. Each method constructs first a model of DM's preferences and then exploits this model in order to workout a recommendation. A large class of methods proposed in the literature use an outranking relation as a preference model (whose semantic is "at least as good as"). In order to implement these methods in real-world applications, the values of preference parameters, like importance coefficients and discrimination thresholds, are to be given by the DM. As this is usually a difficult task, we propose to infer values of these parameters from examples of decisions supplied by the DM. Such an approach to preference modeling is called aggregation/disaggregation approach. The paper describes an implementation of an outranking method integrating this kind of preference elicitation support.