Combination of a modified fuzzy network DEA approach with ML algorithms and its application in the automobile manufacturing industry
Fereshteh Koushki
1
(
Department of Mathematics, Qazvin Branch, Islamic Azad University, Qazvin, Iran.
)
Mona Naghdehforoushhaa
2
(
Department of Computer Engineering, Takestan Branch, Islamic Azad University, Takestan, Iran
)
Keywords: Data envelopment analysis (DEA), Performance evaluation, Fuzzy Network DEA, Machine Learning (ML) algorithms, After-sales services.,
Abstract :
The production of goods and the provision of services involve multi-process operations. Evaluating production operations and services to optimally allocate resources, reduce costs, ensure customer satisfaction, and achieve similar objectives is fundamental in management and decision-making. On the other hand, in many cases, accurate and sufficient information is not available, and the data is imprecise. Structural complexity and imprecise data lead to a large volume of variables and constraints in models that assess the performance of systems. The use of artificial intelligence (AI) techniques, such as Machine Learning (ML) algorithms, is impressive for accurately predicting the performance scores of network systems in fuzzy data environments. This paper proposes, for the first time, an integration of a new fuzzy network Data Envelopment Analysis (DEA) approach with AI techniques to predict the efficiency score of multi-process production and service systems. The findings indicate that of the three AI algorithms examined- Logistic Regression (LR), Random Forest (RF), and Decision Tree (DT)- the RF algorithm has almost the highest accuracy in predicting interval efficiency scores.
References
[1] Batta M. (2020). Machine learning algorithms - A review. Int. J. Sci. Res. (IJ), 9 (1).
[2] Charnes, A., Cooper, W.W. & Rhodes, E. (1978). Measuring the efficiency of decision making units. European Journal of Operational Research, 2, 429–444.
[3] Chen, Y., Cook, W. D., Li, N. & Zhu, J. (2009). Additive efficiency decomposition in two-stage DEA. European Journal of Operational Research, 196, 1170-1176.
[4] Ebrahimnejad, A., Amani, N. (2021). Fuzzy data envelopment analysis in the presence of undesirable outputs with ideal points. Complex Intell, Syst. 7, 379–400.
[5] Emami L. hosseinzadeh lotfi F. & Rostamy Malkhalifeh M. (2024). Fixed cost allocation in bank branches: A network DEA approach. International Journal of Finance & Managerial Accounting, 9(35), 15-30.
[6] Färe, R. & Primont, D. (1984). Efficiency measures for multi plant firms. Operations Research Letters, 3, 257-260.
[7] Fukuyama, H. & Matousek, R. (2017). Modeling Bank Performance: A Network DEA Approach. European Journal of Operational Research, 259 (2), 721-732.
[8] Fukuyama, H. & Mirdehghan, S. M. (2012). Identifying the efficiency status in network DEA. European Journal of Operational Research, 220(1), 85-92.
[9] Fukuyama H, Tsionas M, Tan Y. (2023). Dynamic network data envelopment analysis with a sequential structure and behavioural-causal analysis: Application to the Chinese banking industry. European Journal of Operational Research, 307(3). 1360_1373.
[10] Galagedera, D. U. A., Roshdi, I., Fukuyama, H. & Zhu, J. (2018). A new network DEA model for mutual fund performance appraisal: An application to U.S. equity mutual funds. Omega, 77, 168-179.
[11] Guggari, S., Kadappa, V., & Umadevi, V. (2018). Non-sequential partitioning approaches to decision tree classifier. Future Comput. Inform. J, 3, 275–285.
[12] Hatami-Marbini A. (2019). Benchmarking with network dea in a fuzzy environment. RAIRO-Oper. Res., 53(2) 687-703.
[13] Hosmer, D.W., and Lemeshow, S. (2000). Applied Logistic Regression, 2000, Wiley online library.
[14] Jomthanachai, S., Wong, W-P, & Lim, C-P. (2021) An Application of Data Envelopment Analysis and Machine Learning Approach to Risk Management, in IEEE Access, 9, 85978-85994.
[15] Kao, C. & Hwang, S-N. (2008). Efficiency decomposition in two-stage data envelopment analysis: An application to non-life insurance companies in Taiwan. European journal of operational research, 185 (1), 418–429.
[16] Kooshki, F., Mashayekhi Nezam Abadi, E. (2018). A Network DEA Approach to Assess Supply Chains and its Application in Medical Industry. Journal of Quality Engineering and Management, 8(1), 37-48.
[17] Koulinas, G., Paraschos, P., & Koulouriotis, D. (2020). A Decision Trees-based knowledge mining approach for controlling a complex production system. Procedia Manuf, 51, 1439–1445.
[18] Koushki, F. (2017). Modeling Dynamic Production Systems with Network Structure. Iranian Journal of Mathematical Sciences and Informatics, 12(1), 13-26.
[19] Koushki F. (2018). Performance measurement and productivity management in production units with network structure by identification the most productive scale size pattern. International Journal of Supply and Operations Management 5 (4), 379-395
[20] Koushki F. (2023). Centralized DEA Approach to Assess Efficiency Scores of Bank Branches with Foreign Exchange Transactions. j. Ind. Manage. Studies ,21 (69), 235-270.
[21] Kuo, R., Wang, Y., & Tien, F. (2010). Integration of artificial neural network and MADA methods for green supplier selection. Journal of Cleaner Production, 18(12), 1161-1170.
[22] Lee, J., Keck, J. (2022). Embracing Analytics in the Drinking Water Industry. IWA Publishing London, UK.
[23] Liu, S-T. (2014). Fuzzy efficiency ranking in fuzzy two-stage data envelopment analysis. Optimization Letters, 8(2), 633-652.
[24] Lu, T. (2021). A Fuzzy Network DEA Approach to the Selection of Advanced Manufacturing Technology. Sustainability, 13, 4236.
[25] Niknafs j., Keramati M.A., Haghighat Monfared J. (2020). Estimating Efficiency of Bank Branches by Dynamic Network Data Envelopment Analysis and Artificial Neural Network. Advances in Mathematical Finance & Applications, 5(3), 377-390.
[26] Qin R, Liu Y, Liu Z, Wang G (2009). Modeling fuzzy DEA with type-2 fuzzy variable coefficients. Lecture notes in computer science. Springer, Heidelberg, 25–34.
[27] Ramos, D., Faria, P., Morais, A., & Vale, Z. (2022). Using decision tree to select forecasting algorithms in distinct electricity consumption context of an office building. Energy Rep, 8 (3), 417–422.
[28] Rebelo CGS, Pereira MT, Silva JFG, Ferreira LP, Sa JC, Mota AM. (2021). After sales service: key settings for improving profitability and customer satisfaction. Procedia Manufacturing, 55: 463 -470.
[29] Rezaee, M.J., Onari, M.A., & Saberi, M. (2024). A data-driven decision support framework for DEA target setting: an explainable AI approach. Engineering Applications of Artificial Intelligence, 127(A),107222.
[30] Sahil M.A. & Danish Lohani Q.M. (2024). Comprehensive intuitionistic fuzzy network data envelopment analysis incorporating undesirable outputs and shared resources. MethodsX, 12(102710).
[31] Sarker, I.H. (2021). Machine Learning: Algorithms, Real-World Applications and Research Directions. SN COMPUT. SCI. 2, 160.
[32] Sengupta JK. (1992). A fuzzy systems approach in data envelopment analysis. Comput Math Appl, 24:259–266.
[33] Shafiei Nikabadi M, Yakideh K. (2017). oveysi omran A. Presenting Network data envelopment analysis models by a combination of desired and undesired intermediate and final outputs. Jor, 14 (1) :95-116.
[34] Shahbazifar MS, Matin RK, Khounsiavash M & Koushki F. (2021). Group ranking of two-stage production units in network data envelopment analysis. RAIRO-Operations Research, 55 (3), 1825-1840.
[35] Shi, Y., & Zhao, W. (2023). An Integrated machine learning and DEA-predefined performance outcome prediction framework with high-dimensional imbalanced data. INFOR: Information Systems and Operational Research, 62(1), 100–129.
[36] Shokri Kahi, V., Yousefi, S., Shabanpour, H. & Farzipoor Saen, R. (2017). How to evaluate sustainability of supply chains? A dynamic network DEA approach. Industrial Management & Data Systems, 117(9), 1866-1889.
[37] Singh N, Pant M. (2020). Efficiency assessment of Indian paper mills through fuzzy DEA. Mater Manuf Process, 35(6):725–736.
[38] Soofizadeh, S., & Fallahnejad, R. (2022). A bargaining game model for performance evaluation in network DEA considering shared inputs in the presence of undesirable outputs. J. Math. Model. 10(2), 227-245.
[39] Sotiros D., Koronakos G., Despotis D. K. (2019). Dominance at the divisional efficiencies level in network DEA: The case of two-stage processes, Omega, 85, 144-155.
[40] Tone, K. & Tsutsui, M. (2014). Dynamic DEA with network structure: a slacks-based measure approach. Omega, 42(1), 124-131.
[41] Vlahogianni, E. I., Kepaptsoglou, K., & Karlaftis, M. G. (2016). Modelling the performance of the Athens Bus Network using data envelopment analysis and neural network regression. Journal of Transport Economics and Policy (JTEP), 50(4), 369-383.
[42] Wanke, P., Ostovan, S., Mozaffari, M.R., Gerami, J. and Tan, Y. (2023). Stochastic network DEA-R models for two-stage systems. Journal of Modelling in Management, Vol. 18 No. 3, 842-875.
[43] Xiao S., Dominikos Kremantzis M., Sotirios Kyrgiakos L., Vlontzos G & Pardalos P.M., 2024. Embracing fairness within a cross-efficiency hierarchical network DEA system. Operational Research, Springer, 24(1), 1-31.
[44] Yang Z. Guo S. Tang H. Tan T. Du B. Huang L. (2022). The fuzzy DEA-based manufacturing service efficiency evaluation and ranking approach for a parallel two-stage structure of a complex product system on the example of solid waste recycling. Processes, 10:2322.
[45] Yang, F., Wu, D., Liang, L., Bi, G. & Wu, D.D. (2011). Supply chain DEA: production possibility set and performance evaluation model. Annals of Operations Research, 185, 195-211.
[46] Yang, S., & Yang X. (2025). A new uncertain two-stage network DEA model based on chance-constrained programming. Journal of Industrial and Management Optimization, 21(3), 2032-2051.
[47] Yu VF, Dat LQ (2014). An improved ranking method for fuzzy numbers with integral values. Appl Soft Comput,14:603–608.
[48] Zadeh LA. (1965). Fuzzy sets. Inf Control, 8:338–353.
[49] Zadmirzaei, M., Hasanzadeh, F., Susaeta, A. and Gutiérrez E. (2024). A novel integrated fuzzy DEA–artificial intelligence approach for assessing environmental efficiency and predicting CO2 emissions. Soft Comput, 28, 565–591.
[50] Zhang, Z., Xiao, Y., & Niu, H. (2022) DEA and Machine Learning for Performance Prediction. Mathematics, 10, 1776.
[51] Zheng, Y., Li, J., & Cai, X. (2024). Two-sided platform customer classification system based on network DEA: an application to an on-demand freight platform. International Journal of Systems Science: Operations & Logistics, 11(1).
[52] Zhou Z., Lin, L., Xiao, H., Ma, Ch. & Wu, Sh. (2017). Stochastic network DEA models for two-stage systems under the centralized control organization mechanism. Computers & Industrial Engineering, 110, 404-412.
[53] Zhou X, Xu Z., Chai J., Yao L., Wang S., Lev B. (2019). Efficiency evaluation for banking system under uncertainty: A multi-period three-stage DEA model. Omega, 85, 68-82.