Eliminating congestion of decision-making units using inverse data envelopment analysis

Abstract

This survey proposes a new application of the inverse data envelopment analysis (InvDEA) in the problem of merging decision-making units (DMUs) to improve the performance of DMUs by removing congestion. Congestion is a factor in reducing production; therefore, removing it decreases costs and increases outputs. There are two significant subjects in the merging DMUs. Estimating the inherited inputs and outputs of a new production DMU with no congestion is the first problem while achieving a pre-specified efficiency level from the merged DMU is the second one. Both problems are examined using the ideas of inverse DEA and congestion. Using Pareto solutions to multiple-objective programming problems, sufficient conditions for inherited input/output estimates with no congestion and increasing efficiency are created. Besides, an example is perused for the reliability of the proposed approach in basic research institutes in the Chinese Academy of Science (CAS) in 2010.

Keywords

• data envelopment analysis (dea)
• congestion
• merging
• inverse dea
• multiple-objective programming