Volume 5 • Issue 2 • PP: 48–55 • 2026
A Machine Learning-Enhanced Data Envelopment Analysis Framework for Predicting Institutional Efficiency in Higher Education
Open Access & Copyright
© 2026 The Author(s). Published by ASPG. This article is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
View PDF Abstract
The paper presents a novel approach for predicting the efficiency of engineering higher educational institutions in India. The prediction model uses data envelopment analysis to solve linear programming problems and support vector regression as a supervised machine learning algorithm. DEA is a nonparametric tool for computing the relative efficiency of HEIs across multiple inputs and outputs. A total of 25 featured variables is considered, out of which 15 are input-oriented, whereas 10 are output-oriented. Input-oriented features are normalised using the standard z-score method, whereas output-oriented features are normalised using the Min–Max normalised method. A sample of 7432 engineering institutions is considered for the featured dataset. The featured dataset is split at a 90:10 ratio for training and testing. The hybrid model, combining traditional DEA with a supervised machine learning SVR, is trained on a training dataset. The prediction model is tested for estimating 743 engineering institutions. The model provides higher accuracy, along with a precision score, in the confusion matrix comparing the actual and predicted HEI performance categories. The best-fitting hybrid model also yields a predicted efficiency index for engineering HEIs, along with MAE, MSE, and RMSE, which are 0.0703, 0.0080, and 0.0894, respectively. The R-squared score of the prediction model is 0.7642. The developed predictive model can be generalised across sectors such as agriculture, banking, industry, and education.
Keywords
References
[1] Department of Higher Education, Ministry of Education, Government of India, “All india survey on higher education 2021–22,” Government of India, New Delhi, Tech. Rep., 2023.
[2] Ministry of Human Resource Development, Government of India, “National education policy 2020,” Government of India, New Delhi, Tech. Rep., 2020.
[3] National Assessment and Accreditation Council, “Assessment and accreditation,” accessed: Nov. 18, 2024.
[4] National Institutional Ranking Framework, “Parameters,” accessed: Dec. 31, 2025.
[5] Department of Higher Education, Ministry of Education, Government of India, “India rankings 2024,” National Institutional Ranking Framework, New Delhi, Tech. Rep., Aug. 2024.
[6] Y. Cheng, J. Peng, Z. Zhou, X. Gu, and W. Liu, “A hybrid DEA-AdaBoost model in supplier selection for fuzzy variable and multiple objectives,” IFACPapersOnLine, vol. 50, no. 1, pp. 12 255–12 260, Jul. 2017.
[7] Z. Zhang, Y. Xiao, and H. Niu, “DEA and machine learning for performance prediction,” Mathematics, vol. 10, no. 10, p. 1776, May 2022.
[8] N. Zhu, C. Zhu, and A. Emrouznejad, “A combined machine learning algorithms and DEA method for measuring and predicting the efficiency of chinese manufacturing listed companies,” Journal of Management Science and Engineering, vol. 6, no. 4, pp. 435–448, Dec. 2021.
[9] Y. Khoubrane, N. A. Ramli, and S. S. M. Khairi, “Performance measurement: Machine learning as a complement to DEA for continuous efficiency estimation,” Malaysian Journal of Fundamental and Applied Sciences, vol. 20, no. 2, pp. 288–301, Mar. 2024.
[10] P. Luangpaiboon, C. Phinkrathok, W. Atthirawong, and P. Aungkulanon, “Driving educational excellence: A data envelopment analysis study for decisionmaking enhancement,” SAGE Open, vol. 14, no. 2, p. 21582440241261008, Jun. 2024.
[11] M. G. Perroni, C. P. da Veiga, E. Forteski, D. A. B. Marconatto, W. V. da Silva, C. O. Senff, and Z. Su, “Integrating relative efficiency models with machine learning algorithms for performance prediction,” SAGE Open, vol. 14, no. 2, p. 21582440241257800, Jun. 2024. 54.
[12] S. Yang, Y. Ogawa, K. Ikeuchi, R. Shibasaki, and Y. Okuma, “Post-hazard supply chain disruption: Predicting firm-level sales using graph neural network,” International Journal of Disaster Risk Reduction, vol. 110, p. 104664, Aug. 2024.
[13] J. L. Zofio, J. Aparicio, J. Barbero, and J. M. Zabala-Iturriagagoitia, “Benchmarking performance through efficiency analysis trees: Improvement strategies for colombian higher education institutions,” Socio- Economic Planning Sciences, vol. 92, p. 101845, Apr. 2024.
[14] Y. Shi and W. Zhao, “An integrated machine learning and DEA-predefined performance outcome prediction framework with high-dimensional imbalanced data,” INFOR: Information Systems and Operational Research, vol. 62, no. 1, pp. 100–129, 2024.
[15] A. R. Dipierro and K. De Witte, “The underlying signals of efficiency in european universities: A combined efficiency and machine learning approach,” Studies in Higher Education, vol. 50, no. 6, pp. 1306–1325, Jun. 2025.
[16] Implementation Core Committee, National Institutional Ranking Framework, “India rankings 2024: Methodology for ranking of academic institutions in india— ranking metrics for engineering,” Ministry of Education, Government of India, New Delhi, Tech. Rep., 2024.
[17] J. P. S. Joorel, A. Kumar, H. Solanki, V. Raja, D. Shah, P. Pradhan, K. Trivedi, and P. Singh, “Five years of india rankings (2016–2020): An evolutionary study,” DESIDOC Journal of Library and Information Technology, vol. 41, no. 1, pp. 42–48, Jan. 2021.
[18] Clarivate, “Web of science,” citation database; accessed Nov. 18, 2024.
[19] Elsevier, “Scopus,” abstract and citation database; accessed Nov. 18, 2024.
Cite This Article
Choose your preferred format
Publisher's Note
The statements, opinions, and data presented in this article are solely those of the author(s) and do not necessarily represent those of ASPG, the journal, or its editors. ASPG and the editors disclaim responsibility for any harm arising from the use of any ideas, methods, instructions, or products described in this article, to the fullest extent permitted by applicable law.