大数据背景下DEA方法的加速算法研究

doi:10.16381/j.cnki.issn1003-207x.2023.1157

Abstract

Abstract:

Data envelopment analysis （DEA）， a data-driven， multi-attribute， nonparametric approach， has been widely applied in performance evaluation， resource allocation， cost analysis， and related fields， and has become an important methodology in operations management. In recent years， the explosive growth in the variety and scale of data generated by the rapid development of modern society has posed new challenges to the DEA methodology， which had previously reached a relatively mature stage. In the context of big data， the increasing number of indicators and decision-making units， together with rising data complexity， has led to a sharp increase in the computational time required by DEA models. Based on a systematic review of existing theoretical and methodological approaches for accelerating DEA computation， as well as their respective advantages and limitations， this study proposes a computationally efficient acceleration algorithm for single-machine， single-thread DEA implementation. The proposed algorithm can substantially reduce the computational time of DEA models and is shown to possess strong data-cleaning capability. The algorithm is applied to real financial statement data from Chinese A-share listed companies from 2016 to 2021， as well as two simulated datasets， to validate its data-cleaning capability and further demonstrate its practical value.

Key words: data envelopment analysis, big data, computation acceleration

CLC Number:

Qingyuan Zhu,Shuqi Xu,Yinghao Pan, et al. The Computation Acceleration of DEA in the Big Data Context[J]. Chinese Journal of Management Science, 2026, 34(10): 107-117.

Figures/Tables 10

References 46

[1]	李国杰，程学旗. 大数据研究：未来科技及经济社会发展的重大战略领域——大数据的研究现状与科学思考［J］. 中国科学院院刊， 2012， 27（6）： 647-657.
	Li G J， Cheng X Q. Research status and scientific thinking of big data［J］. Bulletin of the Chinese Academy of Sciences， 2012， 27（6）： 647-657.
[2]	Adams J U. Genetics： Big hopes for big data［J］. Nature， 2015， 527（7578）： S108-S109.
[3]	Einav L， Levin J. Economics in the age of big data［J］. Science， 2014， 346（6210）： 1243089.
[4]	Frégnac Y. Big data and the industrialization of neuroscience： A safe roadmap for understanding the brain？［J］. Science， 2017， 358（6362）： 470-477.
[5]	Sagiroglu S， Sinanc D. Big data： A review［C］//Proceedings of 2013 International Conference on Collaboration Technologies and Systems （CTS）， San Diego， CA， USA， May 20-24， IEEE， 2013： 42-47.
[6]	陈国青，吴刚，顾远东，等. 管理决策情境下大数据驱动的研究和应用挑战——范式转变与研究方向［J］. 管理科学学报， 2018， 21（7）： 1-10.
	Chen G Q， Wu G， Gu Y D， et al. The challenges for big data driven research and applications in the context of managerial decision-making： Paradigm shift and research directions［J］. Journal of Management Sciences in China， 2018， 21（7）： 1-10.
[7]	Charnes A， Cooper W W， Rhodes E. Measuring the efficiency of decision making units［J］. European Journal of Operational Research， 1978， 2（6）： 429-444.
[8]	Banker R D， Charnes A， Cooper W W. Some models for estimating technical and scale inefficiencies in data envelopment analysis［J］. Management Science， 1984， 30（9）： 1078-1092.
[9]	Seiford L M， Zhu J. Profitability and marketability of the top 55 U.S. commercial banks［J］. Management Science， 1999， 45（9）： 1270-1288.
[10]	Podinovski V V. Variable and constant returns-to-scale production technologies with component processes［J］. Operations Research， 2022， 70（2）： 1238-1258.
[11]	Sueyoshi T. Measuring efficiencies and returns to scale of Nippon telegraph & telephone in production and cost analyses［J］. Management Science， 1997， 43（6）： 779-796.
[12]	Staub R B， da Silva e Souza G， Tabak B M. Evolution of bank efficiency in Brazil： A DEA approach［J］. European Journal of Operational Research， 2010， 202（1）： 204-213.
[13]	Sueyoshi T， Goto M. Weak and strong disposability vs. Natural and managerial disposability in DEA environmental assessment： Comparison between Japanese electric power industry and manufacturing industries［J］. Energy Economics， 2012， 34（3）： 686-699.
[14]	Mao W， Koo W W. Productivity growth， technological progress， and efficiency change in Chinese agriculture after rural economic reforms： A DEA approach［J］. China Economic Review， 1997， 8（2）： 157-174.
[15]	O’Neill L， Rauner M， Heidenberger K， et al. A cross-national comparison and taxonomy of DEA-based hospital efficiency studies［J］. Socio-Economic Planning Sciences， 2008， 42（3）： 158-189.
[16]	Wu J， Zhu Q， Chu J， et al. Measuring energy and environmental efficiency of transportation systems in China based on a parallel DEA approach［J］. Transportation Research Part D： Transport and Environment， 2016， 48： 460-472.
[17]	Sinuany-Stern Z. Foundations of operations research： From linear programming to data envelopment analysis［J］. European Journal of Operational Research， 2023， 306（3）： 1069-1080.
[18]	Dulá J H. Data envelopment analysis （DEA）： Algorithms， computations， and Geometry［M］// Charles V， Aparicio J， Zhu J. Data Science and Productivity Analytics. Cham： Springer， 2020： 35-56.
[19]	Farrell M J. The measurement of productive efficiency［J］. Journal of the Royal Statistical Society Series A （General）， 1957， 120（3）： 253-290.
[20]	Cook W D， Seiford L M. Data envelopment analysis （DEA）–Thirty years on［J］. European Journal of Operational Research， 2009， 192（1）： 1-17.
[21]	Tone K. A slacks-based measure of efficiency in data envelopment analysis［J］. European Journal of Operational Research， 2001， 130（3）： 498-509.
[22]	Wei Q， Zhang J， Zhang X. An inverse DEA model for inputs/outputs estimate［J］. European Journal of Operational Research， 2000， 121（1）： 151-163.
[23]	Kerstens K， Van de Woestyne I. Negative data in DEA： A simple proportional distance function approach［J］. Journal of the Operational Research Society， 2011， 62（7）： 1413-1419.
[24]	Kuosmanen T， Matin R K. Theory of integer-valued data envelopment analysis［J］. European Journal of Operational Research， 2009， 192（2）： 658-667.
[25]	陈金晓，陈剑. 考虑断链风险的供应链绩效测度与Nash谈判［J］. 管理科学学报， 2023， 26（1）： 1-18.
	Chen J X， Chen J. Supply chain performance measurement and Nash bargaining considering the risk of chain break［J］. Journal of Management Sciences in China， 2023， 26（1）： 1-18.
[26]	Adler N， Olesen O B， Volta N. Identifying merger opportunities： The case of air traffic control［J］. Operations Research， 2024， 72（1）： 389-409.
[27]	Olesen O B， Petersen N C. Indicators of ill-conditioned data sets and model misspecification in data envelopment analysis： An extended facet approach［J］. Management Science， 1996， 42（2）： 205-219.
[28]	Dakpo K H， Jeanneaux P， Latruffe L. Modelling pollution-generating technologies in performance benchmarking： Recent developments， limits and future prospects in the nonparametric framework［J］. European Journal of Operational Research， 2016， 250（2）： 347-359.
[29]	Chen Y， Cook W D， Kao C， et al. Network DEA pitfalls： Divisional efficiency and frontier projection［M］//Cook W D，Zhu J. Data Envelopment Analysis： A Handbook on the Modeling of Internal Structures and Networks. Boston， MA： Springer， 2014： 31-54.
[30]	孟小峰，慈祥. 大数据管理：概念、技术与挑战［J］. 计算机研究与发展， 2013， 50（1）： 146-169.
	Meng X F， Ci X. Big data management： Concepts， techniques and challenges［J］. Journal of Computer Research and Development， 2013， 50（1）： 146-169.
[31]	Sueyoshi T， Chang Y L. Efficient algorithm for additive and multiplicative models in data envelopment analysis［J］. Operations Research Letters， 1989， 8（4）： 205-213.
[32]	Ali A I. Streamlined computation for data envelopment analysis［J］. European Journal of Operational Research， 1993， 64（1）： 61-67.
[33]	Dulá J H， López F J. Preprocessing DEA［J］. Computers & Operations Research， 2009， 36（4）： 1204-1220.
[34]	Dulá J H. A computational study of DEA with massive data sets［J］. Computers & Operations Research， 2008， 35（4）： 1191-1203.
[35]	Barr R S， Durchholz M L. Parallel and hierarchical decomposition approaches for solving large-scale Data Envelopment Analysis models［J］. Annals of Operations Research， 1997， 73： 339-372.
[36]	Zhu Q， Wu J， Song M. Efficiency evaluation based on data envelopment analysis in the big data context［J］. Computers & Operations Research， 2018， 98： 291-300.
[37]	Dellnitz A. Big data efficiency analysis： Improved algorithms for data envelopment analysis involving large datasets［J］. Computers & Operations Research， 2022， 137： 105553.
[38]	Korhonen P J， Siitari P A. A dimensional decomposition approach to identifying efficient units in large-scale DEA models［J］. Computers & Operations Research， 2009， 36（1）： 234-244.
[39]	Dulá J H. An algorithm for data envelopment analysis［J］. INFORMS Journal on Computing， 2011， 23（2）： 284-296.
[40]	Jie T. Parallel processing of the Build Hull algorithm to address the large-scale DEA problem［J］. Annals of Operations Research， 2020， 295（1）： 453-481.
[41]	Chen W C， Lai S Y. Determining radial efficiency with a large data set by solving small-size linear programs［J］. Annals of Operations Research， 2017， 250（1）： 147-166.
[42]	Khezrimotlagh D， Zhu J， Cook W D， et al. Data envelopment analysis and big data［J］. European Journal of Operational Research， 2019， 274（3）： 1047-1054.
[43]	Khezrimotlagh D， Zhu J. Data envelopment analysis and big data： Revisit with a faster method［M］//Charles V， Aparicio J， Zhu J.Data Science and Productivity Analytics. Cham： Springer， 2020： 1-34.
[44]	Zhou Y， Wang S， Xu S， et al. Big data in data envelopment analysis with undesirable outputs based on simulation and environmental-health matching data of Chinese industrial enterprises［J］. Annals of Operations Research， 2025， 348（1）： 279-298.
[45]	Cobb C W， Douglas P H. A theory of production［J］. The American Economic Review，1928，18（1）： 139-165.
[46]	Khezrimotlagh D. Simulation designs for production frontiers［J］.European Journal of Operational Research， 2022， 303（3）： 1321-1334.

DMU	投入	产出	分值
A	1	1	142.86
B	4	3	128.57
C	4.1	3	128.57
D	2	1	114.29
E	4	2.9	114.29
F	3	7/3	114.29
G	3	2	114.29

DMU	投入	产出	改进后有效度排序
A	1	1	1
F	3	7/3	2
B	4	3	3
C	4.1	3	4
E	4	2.9	5
G	3	2	6
D	2	1	7

数据	平均值	方差	最大值	最小值
营业总成本（元）	115.83	708.37	28868.87	0.03
营业收入（元）	126.98	762.23	29661.93	0.00
营业外收入（元）	0.37	2.03	106.35	0.00

DMU个数（有效单元个数）	特殊分块法抓取有效单元数目	特殊分块法抓取时间	改进后抓取有效单元数目	改进后抓取时间
500 (31)	26	0.03	27	0.03
1000 (62)	45	0.06	51	0.06
2000 (114)	75	0.16	90	0.15
5000 (266)	130	0.88	142	0.86

The Computation Acceleration of DEA in the Big Data Context

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 46

Related Articles 15

Metrics

Comments

Recommended 0

[1]	Zeshui Xu, Mei Chang, Xunjie Gou. An Analysis of Inter-provincial Carbon Emission Efficiency and Its Influencing Factors in China: A Multi-period Cross-efficiency Approach [J]. Chinese Journal of Management Science, 2026, 34(6): 356-368.
[2]	Zhanxin Ma, Pengbo Hou. Meaning of Super-efficiency, Projection Reliability, and Robust Production Frontiers [J]. Chinese Journal of Management Science, 2026, 34(3): 146-158.
[3]	Jiang Li, Hecheng Wu, Liwen Wang. A Robust Data Envelopment Analysis Model with Common Weights Considering Uncertainty and Its Application [J]. Chinese Journal of Management Science, 2026, 34(3): 333-344.
[4]	Lei Chen, Xu Guo, Yingming Wang. Determination of Optimal Endogenous Direction and Improvement Path in Directional Distance Function [J]. Chinese Journal of Management Science, 2025, 33(9): 89-96.
[5]	Shuya Yan, Guotao Yang, Xun Liang, Zhenyu Guan, Ziyan Liu. Comprehensive Efficiency Evaluation of China’s Economic Development Quality Based on Parallel Two-stage Network DEA Model [J]. Chinese Journal of Management Science, 2025, 33(7): 139-150.
[6]	Ren Mu, Lining Hao, Ankang Li, Shuyi Zhang, Wei Cui. Group Ranking Data Envelopment Analysis Model [J]. Chinese Journal of Management Science, 2025, 33(7): 24-32.
[7]	Suoyi Tan, Mengning Wang, Ye Tian, Jianguo Liu, Xin Lu. Data-Driven Models and Applications on Poverty Identification, Classification, and Prediction [J]. Chinese Journal of Management Science, 2025, 33(5): 124-137.
[8]	Zhanxin Ma, guga Suri. Study of DEA-Malmquist Index Method Based on Frontier Surface Modification [J]. Chinese Journal of Management Science, 2025, 33(3): 118-127.
[9]	Yao Wen, Qingxian An, Yongli Li. Cost DEA Game and Cost Allocation Method Considering the Relative Competitiveness of Decision-making Units [J]. Chinese Journal of Management Science, 2025, 33(2): 71-83.
[10]	Haiyan Wang, Zhaohan Sheng. Modeling of Complex System Management Scenarios Driven by Big Data: Techniques and Processes [J]. Chinese Journal of Management Science, 2025, 33(1): 22-33.
[11]	Guangyu Wan,Feiyan Pu,Zichun Li,Yu Cao. Impact of Marketing Capability and Production Operation Capability on Firms' Financial Performance [J]. Chinese Journal of Management Science, 2024, 32(5): 275-285.
[12]	Xiuli Meng,Jing Yang,Bo Liu. Competition Strategy of Crowdsourcing Logistics Service Quality Based on Big Data Technology [J]. Chinese Journal of Management Science, 2024, 32(4): 130-140.
[13]	YAN Yu-meng, XIONG Xiong, LU Lei, ZHANG Wei, ZHANG Yong-jie. From “A Peek” to “A Strategic View”: Individual Investor Behaviors in the Age of Big Data [J]. Chinese Journal of Management Science, 2023, 31(9): 244-254.
[14]	ZHAO Hui, ZHANG Tao, TANG Ke. How does Agglomeration Affect Entrepreneurial Activities in the North and South? Evidence from High Frequency Full Enterprise Big Data [J]. Chinese Journal of Management Science, 2023, 31(6): 231-240.
[15]	ZHOU Zhen, JIAN Hong-yu, HUANG Jia-pei, LIN Yun. The Influence of E-marketing on Cinema Performance Based on DEA and Grey Entropy [J]. Chinese Journal of Management Science, 2023, 31(5): 240-248.