Ön Lisans Öğrencilerinin Mezuniyetinin Tahmini: Bir Topluluk Öğrenme Yaklaşımı

Abstract

Zamanında mezuniyet, öğrencilere belirli bir meslek veya alanda temel bilgi ve beceriler kazandırmayı ve onları hızla iş gücüne katılmalarını sağlamayı amaçlayan önlisans programlarında başarıyı gösteren önemli bir göstergedir. Ancak, mezuniyet gecikmeleri profesyonel kariyere başlama sürecini erteleyerek ekonomik yükü artırmakta ve psikolojik zorluklara yol açmaktadır. Bu çalışma, öğrencilerin zamanında mezuniyet tahminlerini erken aşamada, yani dönem başında tahmin etmeyi ve zamanında mezun olamayacak risk altındaki öğrencileri belirlemeyi amaçlamaktadır. Böylece, bu risk altındaki öğrenciler için müdahale için zaman kazanılmış olacaktır. Birden fazla modeli birleştirerek oluşturulan topluluk öğrenme yöntemleri ve klasik makine öğrenme modelleri erken tahmin için kullanılmıştır. Modellerin etkinliği, bir devlet üniversitesinin önlisans programından alınan demografik bilgiler, lise başarıları, üniversite giriş sınavı sonuçları ve akademik performans verileri ile incelenmiştir. Sınıflandırma performansı tahminleri üç akademik aşamada yapılmıştır: ilk dönemin başı, ilk dönemin sonu ve ikinci dönemin sonu. Sonuçlar, F1 skoru performans metriğine göre değerlendirilmiş ve dönem başında LR modelinin, diğer iki dönemde ise topluluk öğrenme yöntemlerinin daha iyi performans sergilediği görülmüştür. Ayrıca, dönem içi akademik performans verilerinin kümülatif olarak eklenmesi, tüm modellerin sınıflandırma performanslarını artırmıştır.

Keywords

• Zamanında Mezuniyet
• Eğitim Veri Madenciliği
• Topluluk Öğrenme
• Makine Öğrenimi

Predicting Graduation of Associate Degree Students: An Ensemble Learning Approach

Abstract

On-time graduation is an important indicator of success in associate degree programs that aim to provide students with basic knowledge and skills in a specific profession or field and enable them to quickly enter the workforce. However, graduation delays increase the economic burden and cause psychological difficulties by delaying the process of starting a professional career. This study aims to estimate students' on-time graduation predictions at an early stage, that is, at the beginning of the semester, and to identify at-risk students who may not graduate on time. Thus, time will be gained for intervention for these students at risk. Ensemble learning methods and classical machine learning models, which were created by combining multiple models, were used for early prediction. The effectiveness of the models was examined with demographic information, high school achievements, university entrance exam results and academic performance data obtained from an associate degree program at a state university. Classification performance estimates were made in three academic stages: the beginning of the first semester, the end of the first semester and the end of the second semester. The results were evaluated according to the F1 score performance metric and it was seen that the LR model performed better at the beginning of the semester and the ensemble learning methods performed better in the other two periods. Additionally, cumulatively adding within-term academic performance data increased the classification performances of all models.

Keywords

• On-Time Graduation
• Educational Data Mining
• Ensemble Learning
• Machine Learning

References

1. Bako, H. S., Ambursa, F. U., Galadanci, B. S., Garba, M. (2023). Predicting Timely Graduation of Postgraduate Students Using Random Forests Ensemble Method. Fudma Journal of Sciences, 7(3), 177–185.
2. Rismayati, R., Ismarmiaty, I., Hidayat, S. (2022). Ensemble Implementation for Predicting Student Graduation with Classification Algorithm. International Journal of Engineering and Computer Science Applications (IJECSA), 1(1), 35–42.
3. Pandey, M., Taruna, S. (2014). A Comparative Study of Ensemble Methods for Students' Performance Modeling. International Journal of Computer Applications, 103(8), 26–32.
4. Kang, Z. (2019). Using Machine Learning Algorithms to Predict First-generation College Students’ Six-year Graduation: A Case Study. International Journal of Information Technology and Computer Science, 11(9), 1–8.
5. Desfiandi, A., Soewito, B. (2023). Student Graduation Time Prediction Using Logistic Regression, Decision Tree, Support Vector Machine, and Adaboost Ensemble Learning. IJISCS (International Journal of Information System and Computer Science), 7(3), 195.
6. Law, T.-J., Ting, C.-Y., Ng, H., Goh, H.-N., Quek, A. (2024). Ensemble-SMOTE: Mitigating Class Imbalance in Graduate on Time Detection. Journal of Informatics and Web Engineering, 3(2), 229–250.
7. Ananto, N. (2024). Leveraging Ensemble Learning for Predicting Student Graduation: A Data Mining Approach. Prosiding Seminar Nasional Forum Manajemen Indonesia - e-ISSN 3026-4499, 2(353–365.
8. Anggrawan, A., Hairani, H., Satria, C. (2023). Improving SVM Classification Performance on Unbalanced Student Graduation Time Data Using SMOTE. International Journal of Information and Education Technology, 13(2), 289–295.

9. Ariska, F., Sihombing, V., Irmayani, I. (2022). Student Graduation Predictions Using Comparison of C5.0 Algorithm With Linear Regression. SinkrOn, 7(1), 256–266.
10. Hanafi, W., Chrisnanto, Y. H., Ningsih, A. K. (2023). Student Graduation Prediction System Based on Academic And Non-Academic (Eq) Data Using C4.5 Algorithm. JUMANJI (Jurnal Masyarakat Informatika Unjani), 7(1), 64.
11. Kurniawan, D., Anggrawan, A., Hairani, H. (2020). Graduation Prediction System On Students Using C4.5 Algorithm. MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer, 19(2), 358–365.
12. Lagman, A. C., Alfonso, L. P., Goh, M. L. I., Lalata, J. P., Magcuyao, J. P. H., Vicente, H. N. (2020). Classification Algorithm Accuracy Improvement for Student Graduation Prediction Using Ensemble Model. International Journal of Information and Education Technology, 10(10), 723–727.
13. Mehta, S. (2023). Playing Smart with Numbers: Predicting Student Graduation Using the Magic of Naive Bayes. International Transactions on Artificial Intelligence (ITALIC), 2(1), 60–75.
14. Muliani, S. S., Sihombing, V., Munthe, I. R. (2024). Implementation of Exploratory Data Analysis and Artificial Neural Networks to Predict Student Graduation on-Time. SinkrOn, 8(2), 1188–1199.
15. Rachmawati, D. A., Ibadurrahman, N. A., Zeniarja, J., Hendriyanto, N. (2023). Implementation of the Random Forest Algorithm in Classifying the Accuracy of Graduation Time for Computer Engineering Students at Dian Nuswantoro University. Jurnal Teknik Informatika (Jutif), 4(3), 565–572.
16. Samuel, Y. T., Hutapea, J. J., Jonathan, B. (2019). Predicting the Timeliness of Student Graduation Using Decision Tree C4.5 Algorithm in Universitas Advent Indonesia. In: 2019 12th International Conference on Information & Communication Technology and System (ICTS). IEEE, Surabaya, Indonesia, 276–280
17. Tholib, A., Fadli Hidayat, M. N., Yono, S., Wulanningrum, R., Daniati, E. (2023). Comparison of C4.5 and Naive Bayes for Predicting Student Graduation Using Machine Learning Algorithms. International Journal of Engineering and Computer Science Applications (IJECSA), 2(2), 65–72.
18. Riadi, I., Umar, R., Anggara, R. (2024). Comparative Analysis of Naive Bayes and K-NN Approaches to Predict Timely Graduation using Academic History. International Journal of Computing and Digital Systems, 15(1), 1163–1174.
19. Allen, R. E., Diaz, C., Gant, K., Taylor, A., Onor, I. (2016). Preadmission Predictors of On-time Graduation in a Doctor of Pharmacy Program. American Journal of Pharmaceutical Education, 80(3), 43.
20. Lovelace, M. D., Reschly, A. L., Appleton, J. J. (2017). Beyond School Records: The Value of Cognitive and Affective Engagement in Predicting Dropout and On-Time Graduation. Professional School Counseling, 21(1), 1096-2409–21.1.70.
21. Freund, Y., Schapire, R. E. (1997). A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. Journal of Computer and System Sciences, 55(1), 119–139.
22. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., Gulin, A. (2017). CatBoost: unbiased boosting with categorical features. https://doi.org/10.48550/ARXIV.1706.09516
23. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., Liu, T.-Y. (2017). LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In: 31st Conference on Neural Information Processing Systems (NIPS 2017). Long Beach, CA, USA, 1–9
24. Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232.
25. Chen, T., Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, San Francisco California USA, 785–794.
26. Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32.
27. Hosmer, D. W., Lemeshow, S. (2000). Applied Logistic Regression, 1st ed, Wiley, New York.
28. Goodfellow, I., Bengio, Y., Courville, A. (2016). Deep learning, The MIT press, Cambridge.
29. Cortes, C., Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.
30. Breiman, L., Friedman, J. H., Olshen, R. A., Stone, C. J. (2017). Classification And Regression Trees, 1st ed, Routledge, New York.