Modeling Uncertainty in Multi Criteria Decision Analysis (MCDA) Problems: A Probabilistic TOPSIS Model using Bayesian Belief Networks (BBNs) (BBNTOPSIS)

TOPSIS (technique for order preference by similarity to ideal solution), one of the MCDA (multi-criteria decision analysis) methods, is a technique to evaluate the performance of alternatives through the similarity with the ideal solution. Despite its popularity and simplicity in concept, this technique is often criticized because of its inability to deal adequately with uncertainty and imprecision inherent in the process of mapping the perceptions of decision-makers. In order to overcome this challenge, this paper presents a probabilistic model based on Bayesian belief networks (BBNs) -a state-of-the-art technique in modeling uncertainty. BBNs provide a framework for presenting causal relationships and enables probabilistic inference among a set of variables. The new approach explicitly quantifies uncertainty in TOPSIS formulation and also provides an appropriate method for modeling experts’ knowledge, and updating the outranking results with respect to new believes and evidences. The capabilities of proposed approach are explained by a project supplier selection problem.

کلیدواژه ها:

MCDA ، TOPSIS ، Bayesian belief networks (BBNs) ، uncertainty ، outranking