A DEA-based incentive approach for allocating common revenues or fixed costs

• Published in: European journal of operational research Vol. 292; no. 2; pp. 675 - 686
• Main Authors: Dai, Qianzhi, Li, Yongjun, Lei, Xiyang, Wu, Dengsheng
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01-07-2021
• Subjects: Data envelopment analysis (DEA); Fixed cost allocation; Incentives; Proportional sharing; Revenue allocation; Data envelopment analysis (DEA); Fixed cost allocation; Incentives; Proportional sharing; Revenue allocation
• DOI: 10.1016/j.ejor.2020.11.006
• EISSN: 1872-6860
• ISSN: 0377-2217

•We study fixed common revenue or fixed cost allocation problems.•We propose a two-step incentives allocation method.•We provide equations to obtain the global optimal solution of nonlinear allocation models.•We prove several interesting properties of the allocation method.•Several important practical insights are also obtained.
In practice, the concept of incentives is extensively applied in the allocation process for guiding the behaviours of an organization's units to satisfy the goals of the organization. However, this concept is rarely considered in data envelopment analysis (DEA)-based allocation research. This paper proposes a two-step incentive approach for allocating common revenues or fixed costs. The first step is performance evaluation. Considering the noncooperative game relationship of decision-making units (DMUs), a DEA game cross-efficiency method is selected to measure the efficiency scores of DMUs in this paper. The second step is incentive allocation. Based on the performance evaluation, we propose our incentive method for allocating revenues or fixed costs. We further provide simple equations to calculate the global optimal solution for our nonlinear programme allocation models. Several properties are explored, and we i) obtain the allocation interval rule of DMUs with the incentives, ii) investigate the quantitative relationship between the allocation gap and the optimal allocation plan, and iii) prove that the optimal allocation plan obtained by our allocation model is unique. The results of an empirical application highlight the applicability of our allocation method and solution approach. In this study, we obtain several important practical insights, including that (i) our method has positive effects on performance improvement and (ii) our method can work well even in an information asymmetric decision-making environment.