An evolutionary approach to preference disaggregation in a MURAME-based credit scoring problem

In this paper we use an evolutionary approach in order to infer the values of the parameters (weights of criteria, preference, indifference and veto thresholds) for developing the multicriteria method MURAME. According to the logic of preference disaggregation, the problem consists in finding the parameters that minimize the inconsistency between the model obtained with those parameters and that one connected with a given reference set of decisions revealed by the decision maker; in particular, two kinds of functions are considered in this analysis, representing a measure of the model inconsistency compared to the actual preferential system. In order to find a numerical solution of the mathematical programming problem involved, we adopt an evolutionary algorithm based on the Particle Swarm Optimization (PSO) method, which is an iterative heuristics grounded on swarm intelligence. The proposed approach is finally applied to a creditworthiness evaluation problem in order to test the methodology on a real data set provided by an Italian bank.