A Hybrid DEA and Decision Tree Framework for Classifying and Ranking Commercial Bank Branches

Authors

https://doi.org/10.48314/ijorai.v1i2.63

Abstract

This study proposes a novel hybrid approach that integrates Data Envelopment Analysis (DEA) with decision tree classification to assess and rank the performance of commercial bank branches based on super-efficiency scores. DEA, specifically the output-oriented Slack-Based Measure (SBM) under Variable Returns to Scale (VRS), is applied to compute super-efficiency scores for 375 bank branches using 22 financial and operational indicators. These scores, capable of exceeding unity, allow differentiation among efficient units and facilitate the construction of a refined performance hierarchy. To enhance interpretability, decision tree models are used to classify branches into three performance categories: Inefficient, Efficient, and Super-Efficient. The tree structure is redefined using a unit-based splitting criterion that prioritizes proximity to benchmark branches in the normalized input-output space. Model evaluation on a test set yields high predictive accuracy (97.3%), with perfect classification for the Super-Efficient category. The results demonstrate the effectiveness of this hybrid methodology in providing both quantitative efficiency metrics and interpretable classification rules, offering valuable insights for managerial decision-making and policy design in the banking sector.

Keywords:

Data envelopment analysis, Decision Tree, Bank branch ranking

References

  1. [1] Charnes, A., Cooper, W. W., & Rhodes, E. (1978). Measuring the efficiency of decision making units. European journal of operational research, 2(6), 429–444. https://doi.org/10.1016/0377-2217(78)90138-8
  2. [2] Andersen, P., & Petersen, N. C. (1993). A procedure for ranking efficient units in data envelopment analysis. Management science, 39(10), 1261–1264. https://doi.org/10.1287/mnsc.39.10.1261
  3. [3] Mozaffari, M. R., Kamyab, P., Jablonsky, J., & Gerami, J. (2014). Cost and revenue efficiency in DEA-R models. Computers and industrial engineering, 78, 188–194. https://doi.org/10.1016/j.cie.2014.10.001
  4. [4] Mozaffari, M. R., Gerami, J., & Jablonsky, J. (2014). Relationship between DEA models without explicit inputs and DEA-R models. Central european journal of operations research, 22(1), 1–12. https://doi.org/10.1007/s10100-012-0273-4
  5. [5] Mozaffari, M. R., Dadkhah, F., Jablonsky, J., & Wanke, P. F. (2020). Finding efficient surfaces in DEA-R models. Applied mathematics and computation, 386, 125497. https://doi.org/10.1016/j.amc.2020.125497
  6. [6] Mozaffari, M. R., Mohammadi, S., Wanke, P. F., & Correa, H. L. (2021). Towards greener petrochemical production: Two-stage network data envelopment analysis in a fully fuzzy environment in the presence of undesirable outputs. Expert systems with applications, 164, 113903. https://doi.org/10.1016/j.eswa.2020.113903
  7. [7] Noura, A. A., Lotfi, F. H., Jahanshahloo, G. R., Rashidi, S. F., & Parker, B. R. (2010). A new method for measuring congestion in data envelopment analysis. Socio-economic planning sciences, 44(4), 240–246. https://doi.org/10.1016/j.seps.2010.06.003
  8. [8] Noura, A. A., Hosseinzadeh Lotfi, F., Jahanshahloo, G. R., & Fanati Rashidi, S. (2011). Super-efficiency in DEA by effectiveness of each unit in society. Applied mathematics letters, 24(5), 623–626. https://doi.org/10.1016/j.aml.2010.11.025
  9. [9] Rashidi, S. F., & Barati, R. (2014). On the comparison of supply chain with Sub-Dmus in Dea. Advances in environmental biology, 8(7), 2387–2390. https://go.gale.com/ps/i.do?id=GALE%7CA385069491&sid=googleScholar&v=2.1&it=r&linkaccess=abs&issn=19950756&p=AONE&sw=w&cookieConsent=true&analyticsOptout=false&userGroupName=anon~3f96368d&aty=open-web-entry
  10. [10] Rashidi, S. F. (2015). Evaluation of productivity indicators in the oil industry by using multi-attribute decision making approach (MADM). International journal of advanced and applied sciences, 2(6), 25–31. https://B2n.ir/kn4618
  11. [11] Aparicio, J., Esteve, M., & Kapelko, M. (2023). Measuring dynamic inefficiency through machine learning techniques. Expert systems with applications, 228, 120417. https://doi.org/10.1016/j.eswa.2023.120417
  12. [12] Guerrero, N. M., Aparicio, J., & Valero-Carreras, D. (2022). Combining data envelopment analysis and machine learning. Mathematics, 10(6), 909. https://doi.org/10.3390/math10060909

Downloads

Published

2025-06-11

Issue

Vol. 1 No. 2 (2025): International Journal of Operations Research and Artificial Intelligence (IJORAI)

Section

Articles

How to Cite

Abdi, A. ., Ahmadinezhad, Z. ., & Habibi, M. . (2025). A Hybrid DEA and Decision Tree Framework for Classifying and Ranking Commercial Bank Branches. International Journal of Operations Research and Artificial Intelligence , 1(2), 74-81. https://doi.org/10.48314/ijorai.v1i2.63