Using a Choquet integral-based approach for incorporating decision-maker's preference judgments in a Data Envelopment Analysis model

In a world in permanent (r)evolution that revolves around money, seeking new ways to contain costs, better allocate resources, and, overall, improve performance is a constant across all fields. Hence, the use of computational methods based on operational research and statistical science is crucial for achieving an appropriate combination of efficiency and effectiveness, especially in domains where the decision-making process is a complex task. This is where Data Envelopment Analysis (DEA) comes in. However, as a non-parametric and, usually, purely objective technique, DEA makes up for what it lacks in incorporating preference information with flexibility and adaptability, which is particularly important in areas where the decision-makers' judgments are crucial. This work proposes a cutting-edge and original approach to fill in this knowledge gap by linking DEA and multiple criteria decision-making with an additive DEA model that takes into account criteria interactivity, by using an inference methodology to determine their weights, and decision-makers' preference information incorporation, by taking advantage of the Choquet multiple criteria preference aggregation model. Thus, this approach was applied to a case study of performance assessment of Portuguese National Healthcare Service secondary healthcare providers across robustness-testing perspectives, generating credible weights stemmed from the decision-maker's judgments and yielding acceptable and valid results. (C) 2020 Elsevier B.V. All rights reserved.