Performance Measurement: Machine Learning as a Complement to DEA for Continuous Efficiency Estimation

被引:0
作者
Khoubrane, Yousef [1 ]
Ramli, Noor Asiah [2 ]
Khairi, Siti Shaliza Mohd [2 ]
机构
[1] Univ Mohammed VI Polytech, EMINES Sch Ind Management, Ben Guerir 43150, Morocco
[2] Univ Teknol MARA, Coll Comp Informat & Math, Sch Math Sci, Shah Alam 40450, Selangor, Malaysia
来源
MALAYSIAN JOURNAL OF FUNDAMENTAL AND APPLIED SCIENCES | 2024年 / 20卷 / 02期
关键词
Data Envelopment Analysis (DEA); Machine Learning (ML); Performance Measurement; DATA ENVELOPMENT ANALYSIS;
D O I
10.11113/mjfas.v20n2.3310
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Data Envelopment Analysis (DEA) is a well -established non -parametric technique for performance measurement to assess the efficiency of Decision -Making Units (DMUs). However, its inability to predict the efficiency values of new DMUs without re -conducting the analysis on the entire dataset has led to the integration of Machine Learning (ML) in previous studies to address this limitation. Yet, such integration often lacks a thorough evaluation of ML's adaptability in replacing the current DEA process. This paper presents the results of an empirical study that employed eight ML models, two DEA variants, and a dataset of S&P500 companies. The findings demonstrated ML's remarkable precision in predicting efficiency values derived from a single DEA run and comparable performance in predicting the efficiency of new DMUs, thus eliminating the need for repeated DEA. This discovery highlights ML's robustness as a complementary tool for DEA in continuous efficiency estimation, rendering the practice of re -conducting DEA unnecessary. Notably, boosting models within the Ensemble Learning category consistently outperformed other models, highlighting their effectiveness in the context of DEA efficiency prediction. Particularly, CatBoost demonstrated its superiority as the top -performing model, followed by LightGBM in the second position in most cases. When extended to five enlarged datasets, it shows that the model exhibits superior R2 values in the CRS scenario.
引用
收藏
页码:288 / 301
页数:14
相关论文
共 33 条
[1]   Data envelopment analysis and data mining to efficiency estimation and evaluation [J].
Anouze, Abdel Latef M. ;
Bou-Hamad, Imad .
INTERNATIONAL JOURNAL OF ISLAMIC AND MIDDLE EASTERN FINANCE AND MANAGEMENT, 2019, 12 (02) :169-190
[2]   TEA-IS: A hybrid DEA-TOPSIS approach for assessing performance and synergy in Chinese health care [J].
Antunes, Jorge ;
Hadi-Vencheh, Abdollah ;
Jamshidi, Ali ;
Tan, Yong ;
Wanke, Peter .
DECISION SUPPORT SYSTEMS, 2023, 171
[3]   Predicting Bank Operational Efficiency Using Machine Learning Algorithm: Comparative Study of Decision Tree, Random Forest, and Neural Networks [J].
Appiahene, Peter ;
Missah, Yaw Marfo ;
Najim, Ussiph .
ADVANCES IN FUZZY SYSTEMS, 2020, 2020
[4]  
Athanassopoulos AD, 1996, J OPER RES SOC, V47, P1000, DOI 10.1057/jors.1996.127
[5]  
Babaei Keshteli H., 2022, International Journal of Data Envelopment Analysis, V10, P57
[6]   SOME MODELS FOR ESTIMATING TECHNICAL AND SCALE INEFFICIENCIES IN DATA ENVELOPMENT ANALYSIS [J].
BANKER, RD ;
CHARNES, A ;
COOPER, WW .
MANAGEMENT SCIENCE, 1984, 30 (09) :1078-1092
[7]  
Bowlin W. F., 1985, ANN OPER RES, V2, P113, DOI [DOI 10.1007/BF01874735, DOI 10.2112/04-0172.1]
[8]   MEASURING EFFICIENCY OF DECISION-MAKING UNITS [J].
CHARNES, A ;
COOPER, WW ;
RHODES, E .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 1978, 2 (06) :429-444
[9]   Short-term load forecasting using a kernel-based support vector regression combination model [J].
Che, JinXing ;
Wang, JianZhou .
APPLIED ENERGY, 2014, 132 :602-609
[10]  
Danieau Pierre-Louis, 2021, Financial Data S&P500 companies