Öz

In recent years, universities have increasingly emphasized performance evaluation in order to remain competitive and to sustain their operations effectively. Considering the wide range of activities carried out by universities, obtaining more reliable results requires classifying variables into meaningful groups rather than evaluating all data as a single whole. Since Data Envelopment Analysis (DEA) relies on the assumption of homogeneity, clustering universities prior to evaluation—rather than analyzing them as a single group—constitutes a more appropriate approach. In this study, universities were grouped using a biclustering method, and the variables employed in performance evaluation were classified into subcategories. Unlike traditional clustering techniques, the biclustering approach simultaneously clusters both decision-making units and variables. A total of 123 universities and 30 variables were analyzed, resulting in three university clusters and four variable subgroups for each cluster. Each university cluster was then evaluated using DEA models, and the most efficient units were identified among the four variable subgroups. This approach enables a more realistic and detailed assessment of university performance by ensuring homogeneous conditions within the DEA framework.

Anahtar Kelimeler

• Biclustering algorithms
• data envelopment analysis
• üniversity performance

Türkiye'deki üniversitelerin performans değerlendirmesi: İkili kümeleme analizi ve en etkili VZA modeline dayalı bir yaklaşım

Öz

Son yıllarda üniversiteler, rekabetçi kalabilmek ve işleyişlerini etkili bir şekilde sürdürebilmek için performans değerlendirmesine giderek daha fazla önem vermektedir. Üniversitelerin yürüttüğü çeşitli faaliyetler göz önüne alındığında, değerlendirme sürecinde tüm verileri tek bir bütün olarak ele almak yerine, değişkenleri anlamlı gruplar halinde sınıflandırmak daha sağlıklı sonuçlar elde edilmesini sağlamaktadır. Veri Zarflama Analizi (VZA) yönteminde homojenlik varsayımı bulunduğundan, üniversiteleri tek bir grup olarak analiz etmek yerine, değerlendirme öncesinde kümelere ayırmak daha uygun bir yaklaşımdır. Bu çalışmada, üniversiteler ikili kümeleme yöntemi kullanılarak gruplandırılmış ve performans değerlendirmesinde kullanılan değişkenler alt kategorilere ayrılmıştır. Geleneksel kümeleme yöntemlerinden farklı olarak, ikili kümeleme yaklaşımında, birimler ve değişkenler eşzamanlı olarak kümelenir. Çalışmada toplam 123 üniversite ve 30 değişken analiz edilerek, 3 üniversite kümesi ve her küme için 4 değişken alt grubu belirlenmiştir. Her üniversite kümesi, VZA modelleri kullanılarak değerlendirilmiş ve 4 değişken alt grubu arasından en etkin birimler tespit edilmiştir. Bu yaklaşım, VZA yöntemi altında homojen koşullar sağlanarak üniversitelerin daha gerçekçi ve ayrıntılı bir şekilde performanslarının değerlendirilmesine olanak tanımaktadır.

Anahtar Kelimeler

• İkili kümeleme algoritmaları
• veri zarflama analizi
• üniversite performansı

Teşekkür

Yazarlar, makalenin dilbilgisi ve yazım kontrolünü sağladıkları için Gazi Üniversitesi Akademik Yazım Uygulama ve Araştırma Merkezi'ne teşekkür ederler.

Kaynakça

1. 1. 2023 Yükseköğretim değerlendirme ve kalite güvencesi durum raporu, https://www.yokak.gov.tr/documents/StatusReports/Durum_Raporu_2023.pdf, Yayın tarihi Aralık, 2024. Erişim tarihi Temmuz, 2025.
2. 2. Merkezi yönetim bütçesinden AR-GE faaliyetleri için ayrılan ödenek ve harcamalar, https://data.tuik.gov.tr/Bulten/Index?p=Merkezi-Yonetim-Butcesinden-AR-GE-Faaliyetleri-Icin-Ayrilan-Odenek-ve-Harcamalar-2024-53799, Yayın tarihi Ağustos 6, 2024. Erişim tarihi Temmuz, 2025.
3. 3. Yükseköğretim Kurulu, Üniversite izleme ve değerlendirme raporları, https://www.yok.gov.tr/Documents/2024/universite-izleme-ve-degerlendirme-genel-raporu-2024.pdf. Yayın tarihi Ekim 2, 2024. Erişim tarihi Ocak 9, 2025.
4. 4. Charnes A., Cooper W.W., Rhodes E., Measuring the efficiency of decision making units, Eur. J. Oper. Res., 78, 90138-8, 1978.
5. 5. Avkiran N.K., Investigating technical and scale efficiencies of Australian universities through data envelopment analysis, Socioecon Plann Sci, 35, 2001.
6. 6. Abbott M., Doucouliagos C., The efficiency of Australian universities: A data envelopment analysis, Economics of Education Review, 22, 2003.
7. 7. Johnes J., Data envelopment analysis and its application to the measurement of efficiency in higher education, Economics of Education Review, 25, 2006.
8. 8. Kao C., Hung H.T., Efficiency analysis of university departments: An empirical study, Omega (Westport), 36, 2008.

9. 9. Liang L., Li Z.Q., Cook W.D., Zhu J., Data envelopment analysis efficiency in two-stage networks with feedback, IIE Transactions (Institute of Industrial Engineers), 43, 2011.
10. 10. Nazarko J, Šaparauskas J., Application of dea method in efficiency evaluation of public higher education institutions, Technological and Economic Development of Economy, 20, 2014.
11. 11. Lee B.L., Worthington A.C., A network DEA quantity and quality-orientated production model: An application to Australian university research services, Omega (United Kingdom), 60, 2016.
12. 12. Yang G. liang., Fukuyama H., Song Y. yao., Measuring the inefficiency of Chinese research universities based on a two-stage network DEA model, Journal of Informetrics, 12, 2018.
13. 13. Canto M.B., Lopez L.B., Ranking of global efficiency of the best universities in Europe, Marketing and Management of Innovations, 34-47, 2018.
14. 14. Gao Q., He F., Moosa A., Lv Q., The efficiency of technology transfer in Chinese Key Universities, Journal of Scientific and Industrial Research (India), 78, 2019.
15. 15. Zhang X., Shi W., Research about the university teaching performance evaluation under the data envelopment method, Cognit. Syst. Res., 56, 2019.
16. 16. Chen, S. P., Chang, C. W., Measuring the efficiency of university departments: an empirical study using data envelopment analysis and cluster analysis, Scientometrics, 126 (6), 5263-5284, 2021.
17. 17. Singh A.P., Yadav S.P., Tyagi P., Performance assessment of higher educational institutions in India using data envelopment analysis and re-evaluation of NIRF Rankings, International Journal of System Assurance Engineering and Management, 13, 2022.
18. 18. Zhao, L., Wang, D., Yang, F., Zha, Y., Scientific and technological innovation efficiency in Chinese provincial higher education institutions: a three-division network DEA approach, Journal of the Operational Research Society, 76 (1), 111–130, 2024.
19. 19. Torres, L. M. L. d. S., Ramos, F. S., Are Brazilian Higher Education Institutions Efficient in Their Graduate Activities? A Two-Stage Dynamic Data-Envelopment-Analysis Cooperative Approach, Mathematics, 12 (6), 884, 2024.
20. 20. Liu, X., Zhuang, X., Wang, Y., Li, S., Zhang, H., Assessing the internationalization efficiency of China’s higher vocational education: a DEA-Malmquist and three-stage DEA analysis, Cogent Education, 12 (1), 2025.
21. 21. Guo R., Ye M., Input-output efficiency, productivity dynamics, and determinants in western China’s higher education: A three-stage DEA, global Malmquist index, and Tobit model approach, PLOS ONE, 20 (6), e0325901, 2025.
22. 22. Kim N.H., He F., Hong K.R., Kim H.C., Han S.M., A new common weights DEA model based on cluster analysis, Operational Research, 24-29, 2024.
23. 23. Baydan E., Yenigül S.B., Gürel Z.A., New approaches to the rural-urban dilemma: Clustering of settlements with the K-means algorithm., Journal of the Faculty of Engineering and Architecture of Gazi University, 40 (3), 1467-1478, 2025.
24. 24. Carboni O.A., Russu P., Assessing Regional Wellbeing in Italy: An Application of Malmquist–DEA and Self-organizing Map Neural Clustering, Social Indic. Res., 122, 2015.
25. 25. Jahangoshai Rezaee M., Jozmaleki M., Valipour M., Integrating dynamic fuzzy C-means, data envelopment analysis and artificial neural network to online prediction performance of companies in stock Exchange, Physica A, 489, 2018.
26. 26. Bayaraa B., Tarnoczi T., Fenyves V., Measuring performance by integrating k-medoids with dea: Mongolian case, Journal of Business Economics and Management, 20, 2019.
27. 27. Geng Z., Zeng R., Han Y., Zhong Y., Fu H., Energy efficiency evaluation and energy saving based on DEA integrated affinity propagation clustering: Case study of complex petrochemical industries, Energy, 179, 863–875, 2019.
28. 28. Pereira de Souza M.V., Souza R.C., Pessanha J.F.M., da Costa Oliveira C.H., Diallo M., An application of data envelopment analysis to evaluate the efficiency level of the operational cost of Brazilian electricity distribution utilities, Socio-Economic Planning Sciences, 48, 2014.
29. 29. Chen, L., Wang, S. H., Wang, Y. M., A new data envelopment analysis clustering approach within cross-efficiency framework, Journal of the Operational Research Society, 73 (3), 664–673, 2020.
30. 30. Kim, N. H., He, F., Zhang, H., Hong, K. R., Ri, K. C., A data envelopment analysis-based clustering approach under dynamic situations, European Journal of Operational Research, 311(1), 251-262, 2023.
31. 31. Chen, L., Fan, M., Wang, J., A controlled data envelopment analysis clustering approach based on individual perspective, Information Sciences, 677, 120932, 2024.
32. 32. Bozdemir M.K.E., Azkeskin S.A., Akman G., Environmental effıciency analysis to ranking system for all units with undesirable input/output in DEA, Journal of the Faculty of Engineering and Architecture of Gazi University, 39 (4), 2435-2445, 2024.
33. 33. Özsoy V.S., Örkcü H.H., Örkcü M., A simplistic approach without epsilon to choose the most efficient unit in data envelopment analysis, Expert Syst. Appl., 168, 2021.
34. 34. Raponi V., Martella F., Maruotti A., A biclustering approach to university performances: an Italian case study, J. Appl. Stat., 43, 2016.
35. 35. Cheng Y., Church G.M., Biclustering of Expression Data, Proceedings of the 8th International Conference on Intelligent Systems for Molecular Biology, California, 93-103, 2000.
36. 36. Tanay A., Sharan R., Shamir R., Discovering statistically significant biclusters in gene expression data, Bioinformatics, 18, 2002.
37. 37. Madeira S.C., Oliveira A.L., Biclustering algorithms for biological data analysis: a survey, IEEE/ACM Trans. Comput. Biol. Bioinf., 1, 24-45, 2004.
38. 38. Lee D.D., Seung H.S., Learning the parts of objects by non-negative matrix factorization, Nature, 401, 1999.
39. 39. Hafemeister, C., Satija, R., Normalization and variance stabilization of single-cell RNA-seq data using regularized negative binomial regression. Genome Biology, 20, 296, 2019.
40. 40. Dhillon, I. S., Co-clustering documents and words using bipartite spectral graph partitioning, In Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining, New York, 269-274, 2001.
41. 41. Dale J., Zhao J., Obafemi-Ajayi T., Multi-objective Optimization Approach to find Biclusters in Gene Expression Data, IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, Siena-Tuscany, 1-8, 2019.
42. 42. Von Luxburg U., A tutorial on spectral clustering, Stat. Comput., 17, 395-416, 2007.
43. 43. Sexton T.R., Silkman R.H., Hogan A.J., Data envelopment analysis: Critique and extensions, New Directions for Program Evaluation, 32, 73-105, 1986.
44. 44. Andersen P., Petersen N.C., A Procedure for Ranking Efficient Units in Data Envelopment Analysis, Manage Sci., 39 (10), 1261-1264, 1993.
45. 45. Shang J., Sueyoshi T., A unified framework for the selection of a Flexible Manufacturing System, Eur. J. Oper. Res., 85, 1995.
46. 46. Khouja M., The use of data envelopment analysis for technology selection, Comput. Ind. Eng., 28, 1995.
47. 47. Sun S., Assessing computer numerical control machines using data envelopment analysis, Int. J. Prod. Res., 40, 2002.
48. 48. Karsak E.E., Özogul C.O., An integrated decision making approach for ERP system selection. Expert Syst. Appl., 36, 2009.
49. 49. Lam K.F., In the determination of the most efficient decision making unit in data envelopment analysis, Comput. Ind. Eng., 79, 2015.
50. 50. Toloo M., Alternative minimax model for finding the most efficient unit in data envelopment analysis, Comput. Ind. Eng., 81, 2015.
51. 51. Toloo M., Salahi M., A powerful discriminative approach for selecting the most efficient unit in DEA, Comput. Ind. Eng., 115, 2018.
52. 52. Zhang, Z. Y., Nonnegative matrix factorization: models, algorithms and applications, Data Mining: Foundations and Intelligent Paradigms: Volume 2: Statistical, Bayesian, Time Series and other Theoretical Aspects, 99-134, 2012.
53. 53. Sriwastava, B. K., Halder, A. K., Basu, S., Chakraborti, T., RUBic: rapid unsupervised biclustering, BMC bioinformatics, 24 (1), 435, 2023.
54. 54. Li, J., Mei, Q., Yang, C., Zhu, N., Li, G., TransBic: bucket trend-preserving biclustering for finding local and interpretable expression patterns, Briefings in Bioinformatics, 26 (1), bbaf050, 2025.