Developing a new chance-constrained data envelopment analysis in the presence of stochastic data

Outsourcing in logistics is a very significant theme and third-party reverse logistics (3PL) provider evaluation and selection has to be realised in a careful manner in order to provide the expected benefits. Data envelopment analysis (DEA) has been successfully used to select the most efficient supplier(s) in a supply chain. In this study, a new Russell chance-constrained data envelopment analysis (RCCDEA) approach is proposed to assist the decision-makers to determine the most appropriate 3PL providers in the presence of multiple performance measures that are uncertain. Because of the complexity of the proposed model, a genetic algorithm is presented as a solution procedure to obtain near to optimum solutions. The usefulness of the proposed model and algorithm was validated by its application to an illustrative example.