Yükseköğretimde Akademik Başarı Durumunun Erken Tahmini: Yapay Arı Kolonisi ile Optimize Edilmiş Makine Öğrenmesi Modelleri

Öz

Bu çalışmada, yükseköğretimde öğrencilerin mezuniyet ve terk durumlarının erken tahmini için Destek Vektör Makineleri (SVM) ve Ekstra Ağaçlar (ET) modelleri Yapay Arı Kolonisi (ABC) algoritmasıyla optimize edilmiştir. Analizler, birinci dönem sonunda erişilebilir 10 değişken kullanılarak 3.630 öğrenci üzerinde yürütülmüştür. Modeller bağımsız test kümesinde çoklu performans ölçütleriyle değerlendirilmiştir. ABC optimizasyonu her iki modelin performansını artırmış; ABC-SVM 0,907 doğruluk ve 0,941 ROC-AUC ile en yüksek genel başarıyı göstermiştir. ABC-ET ise terk sınıfı duyarlılığında sınırlı üstünlük sağlamıştır. Permütasyon analizi, birinci dönemde başarıyla tamamlanan ders sayısının en belirleyici değişken olduğunu göstermiştir. Bulgular, ABC tabanlı optimizasyonun erken akademik risk tahmininde etkili bir yaklaşım sunduğunu ortaya koymaktadır.

Anahtar Kelimeler

• Akademik başarı tahmini
• Hiperparametre optimizasyonu
• Destek Vektör Makineleri
• Ekstra Ağaçlar

Early Prediction of Academic Success in Higher Education: Optimized Machine Learning Models with Artificial Bee Colonies

Öz

In this study, Support Vector Machines (SVM) and Extra Trees (ET) models were optimized with the Artificial Bee Colony (ABC) algorithm for early prediction of graduation and dropout status of students in higher education. Analyzes were conducted on 3,630 students using 10 accessible variables at the end of the first semester. Models were evaluated with multiple performance measures in an independent test set. ABC optimization increased the performance of both models; ABC-SVM showed the highest overall success with 0.907 accuracy and 0.941 ROC-AUC. ABC-ET, on the other hand, provided limited superiority in dropout class sensitivity. Permutation analysis showed that the number of courses successfully completed in the first semester was the most decisive variable. Findings reveal that ABC-based optimization offers an effective approach to early academic risk prediction.

Anahtar Kelimeler

• Academic achievement prediction
• Hyperparameter optimization
• Support Vector Machines
• Extra Trees

Kaynakça

1. A. Behr, M. Giese, H. D. Teguim Kamdjou, and K. Theune, “Motives for dropping out from higher education—An analysis of bachelor’s degree students in Germany,” Eur. J. Educ., vol. 56, no. 2, pp. 325–343, 2021.
2. S. C. Matz, C. S. Bukow, H. Peters, C. Deacons, A. Dinu, and C. Stachl, “Using machine learning to predict student retention from socio-demographic characteristics and app-based engagement metrics,” Sci. Rep., vol. 13, Art. no. 5705, 2023.
3. M. Delogu, R. Lagravinese, D. Paolini, and G. Resce, “Predicting dropout from higher education: Evidence from Italy,” Econ. Model., vol. 130, Art. no. 106583, 2024.
4. J. Berens, K. Schneider, S. Gortz, S. Oster, and J. Burghoff, “Early detection of students at risk—Predicting student dropouts using administrative student data from German universities and machine learning methods,” J. Educ. Data Min., vol. 11, no. 3, pp. 1–41, 2019.
5. R. Asif, A. Merceron, S. A. Ali, and N. G. Haider, “Analyzing undergraduate students’ performance using educational data mining,” Comput. Educ., vol. 113, pp. 177–194, 2017.
6. V. Christou, I. G. Tsoulos, V. Loupas, A. T. Tzallas, C. Gogos, P. S. Karvelis, N. Antoniadis, E. Glavas, and N. Giannakeas, “Performance and early drop prediction for higher education students using machine learning,” Expert Syst. Appl., vol. 225, Art. no. 120079, 2023.
7. J. Bergstra and Y. Bengio, “Random search for hyper-parameter optimization,” J. Mach. Learn. Res., vol. 13, pp. 281–305, 2012.
8. V. Realinho, J. Machado, L. Baptista, and M. V. Martins, “Predicting student dropout and academic success,” Data, vol. 7, no. 11, Art. no. 146, 2022.

9. V. Realinho, M. V. Martins, J. Machado, and L. Baptista, “Predict students’ dropout and academic success,” UCI Machine Learning Repository [Dataset], 2021.
10. M. V. Martins, L. Baptista, J. Machado, and V. Realinho, “Multi-class phased prediction of academic performance and dropout in higher education,” Appl. Sci., vol. 13, no. 8, Art. no. 4702, 2023.
11. A. Villar and C. R. V. de Andrade, “Supervised machine learning algorithms for predicting student dropout and academic success: A comparative study,” Discov. Artif. Intell., vol. 4, Art. no. 2, 2024.
12. E. C. Umendu, M. Ghanzanfar, A. Kans, and M. A. R. Ahad, “Enhancing student retention in higher education institutions (HEIs): Machine learning approach,” Electronics, vol. 15, no. 4, Art. no. 734, 2026.
13. D. Karaboga and B. Basturk, “On the performance of artificial bee colony (ABC) algorithm,” Appl. Soft Comput., vol. 8, no. 1, pp. 687–697, 2008.
14. Y. Yan, Y. Zhang, and F. Gao, “Dynamic artificial bee colony algorithm for multi-parameters optimization of support vector machine-based soft-margin classifier,”EURASIP J. Adv. Signal Process., vol. 2012, Art. no. 160, 2012.
15. D. Yang, Y. Liu, S. Li, X. Li, and L. Ma, “Gear fault diagnosis based on support vector machine optimized by artificial bee colony algorithm,” Mech. Mach. Theory, vol. 90, pp. 219–229, 2015.
16. K. Mahawar, P. Rattan, A. Jalamneh, M. S. Ab Yajid, O. Abdeljaber, R. Kumar, A. Lasisi, and M. I. Ammarullah, “Employing artificial bee and ant colony optimization in machine learning techniques as a cognitive neuroscience tool,” Sci. Rep., vol. 15, Art. no. 10172, 2025.
17. H. El Yousfi Alaoui, Z. Bousraraf, A. Hjouji, O. El Ogri, and J. El-Mekkaoui, “New regression model for academic achievement and new classification method for school dropout based on Artificial Bee Colony Algorithm,” Stat. Optim. Inf. Comput., vol. 15, no. 5, pp. 3401–3415, 2026.
18. C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, pp. 273–297, 1995.
19. B. E. Boser, I. M. Guyon, and V. N. Vapnik, “A training algorithm for optimal margin classifiers,” in Proc. Fifth Annu. Workshop Comput. Learn. Theory, pp. 144–152, 1992.
20. C.-C. Chang and C.-J. Lin, “LIBSVM: A library for support vector machines,” ACM Trans. Intell. Syst. Technol., vol. 2, no. 3, Art. no. 27, pp. 1–27, 2011.
21. P. Geurts, D. Ernst, and L. Wehenkel, “Extremely randomized trees,” Mach. Learn., vol. 63, pp. 3–42, 2006.
22. D. Karaboga and B. Basturk, “A powerful and efficient algorithm for numerical function optimization: Artificial bee colony (ABC) algorithm,” J. Glob. Optim., vol. 39, no. 3, pp. 459–471, 2007.
23. M. Ulu and E. Kılıç, “Dynamic traffic density prediction in urban areas using machine learning models: Comparative analysis of classification performance,” Int. J. Ind. Eng., vol. 33, no. 2, p. 189, 2026.
24. G. Canbek, T. Taskaya Temizel, and S. Sagiroglu, “PToPI: A comprehensive review, analysis, and knowledge representation of binary classification performance measures/metrics,” SN Comput. Sci., vol. 4, no. 1, Art. no. 13, 2022.