主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

中国管理科学 ›› 2025, Vol. 33 ›› Issue (2): 71-83.doi: 10.16381/j.cnki.issn1003-207x.2022.2113cstr: 32146.14.j.cnki.issn1003-207x.2022.2113

• • 上一篇    下一篇

考虑决策单元间相对竞争力的成本DEA博弈及成本分配方法

文瑶1, 安庆贤2,3(), 李永立4   

  1. 1.福州大学经济与管理学院,福建 福州 350108
    2.中南大学商学院,湖南 长沙 410083
    3.湘江实验室,湖南 长沙 410205
    4.哈尔滨工业大学经济与管理学院,黑龙江 哈尔滨 150001
  • 收稿日期:2022-09-26 修回日期:2022-12-25 出版日期:2025-02-25 发布日期:2025-03-06
  • 通讯作者: 安庆贤 E-mail:anqingxian@163.com
  • 基金资助:
    国家自然科学基金项目(72401067);湖南省科技创新人才计划项目(荷尖)(2022RC1242)

Cost DEA Game and Cost Allocation Method Considering the Relative Competitiveness of Decision-making Units

Yao Wen1, Qingxian An2,3(), Yongli Li4   

  1. 1.School of Economics & Management,Fuzhou University,Fuzhou 350108,China
    2.School of Business,Central South University,Changsha 410083,China
    3.Xiangjiang Laboratory,Changsha 410205,China
    4.School of Management,Harbin Institute of Technology,Harbin 150001,China
  • Received:2022-09-26 Revised:2022-12-25 Online:2025-02-25 Published:2025-03-06
  • Contact: Qingxian An E-mail:anqingxian@163.com

摘要:

合作是企业降低成本的有效策略之一,而合理测量与分配潜在好处是合作成功的关键。对具有竞争关系的合作者来说,其相对竞争力不应因合作而变化。本文首先基于数据包络分析(data envelopment analysis,DEA)与合作博弈论,构建成本DEA博弈,对决策单元(decision making unit, DMU)之间的合作行为进行定量刻画;然后针对该博弈的成本分配问题,提出平等竞争力方法(equal competitiveness method,ECM),最小化任意两个DMU(即合作参与人)在成本分配前后其相对竞争力变化的差异,使其尽可能保持原有的相对竞争力。基于行生成算法及字典式最小最大方法,ECM提供的成本分配方案满足唯一性、有效性、稳定性、对称性、虚拟参与人等性质。最后以3个DMU的算例和25家超市实际数据为例,通过对ECM分配结果、核、Shapley值以及核仁的对比,发现在成本分配后,ECM最能保持DMU的相对竞争力,为企业的合作决策及合作后的成本分配提供参考方案。

关键词: 数据包络分析, 成本分配, 平等竞争力方法, 行生成算法, 字典式最小最大方法

Abstract:

Cooperation is one of the effective strategies for companies to reduce costs; and reasonable measurement and allocation of potential benefits are the key to successful cooperation. For partners with a competitive relationship, their relative competitiveness should not change due to cooperation. A cost DEA game is first built based on data envelopment analysis (DEA) and cooperative game theory, with the aim of quantitatively describing the cooperation between decision making units (DMUs); then, for the cost allocation, an equal competitiveness method (ECM) is proposed to minimize the relative competitiveness changes of any two DMUs (i.e., cooperative players) before and after cost allocation, which makes it possible to maintain relative competitiveness as much as possible. By using the row generation algorithm and lexicographic min-max approach, the cost allocation provided by ECM satisfies uniqueness, effectiveness, stability, symmetry, virtual players, and so on. Finally, taking 3 DMUs and 25 supermarkets as examples, comparing ECM with the core, Shapley value, and nucleolus, it is found that after cost allocation, ECM can best maintain the relative competitiveness of DMUs. It provides a reference for enterprises' managers to make the cooperation decisions, and cost allocation after cooperation in this research.

Key words: data envelopment analysis, cost allocation, equal competitiveness method, row generation algorithm, lexicographic min-max approach

中图分类号: