A simulation-optimization approach using genetic search for supplier selection

The paper presents a simulation-optimization approach using genetic algorithm to the supplier selection problem. The problem consists in selecting a portfolio of suppliers from a set of pre-selected candidates. The supplier selection is a multi-criteria problem that includes both qualitative and quantitative criteria. In order to select the best suppliers it is crucial to make a trade off between these tangible and intangible criteria, some of which may be contradictory. The proposed approach uses discrete-event simulation for performance evaluation of a supplier portfolio and a genetic algorithm for optimum portfolio identification based on performance indices estimated by the simulation. Numerical results on a real-life case study are presented.