A Two-Stage Rough Data Envelopment Analysis and Its Application in Three-Level Supply Chain Performance Evaluation

Abstract

The measure of efficiency for the supply chain is necessary to show productivity and how it uses its resources. One of the most important efficiency measurements is Data Envelopment Analysis (DEA). The traditional DEA model treats the decision-making units (DMUs) as a black box. It considers only the initial inputs and the final outputs. But the internal interactions between subsystems are neglected. This type of DEA is used for straightforward systems, but the complex multistage systems like supply chains, traditional DEA get inaccurate efficiency indicators. As well as, one of the main challenges is the uncertainty of data. The inputs and outputs values are usually required to be deterministic in traditional DEA. Although, this is not a case of real-life problems. Therefore, we develop a mixed innovative approach from Two-stage DEA and rough set theory to produce a modified Two-stage RDEA. The proposed model can measure the efficiency of DMUs comprehensively by considering the internal structure of any supply chain and treating with incomplete and imprecise data. We applied the Two-stage RDEA model in a three-level supply chain to show its applicability to measure the efficiency for both a whole supply chain and all levels comprehensively.