Explainable Machine Learning untuk Prediksi Risiko Dropout Mahasiswa Pendidikan Tinggi Vokasi

M. Fajar Ramadhan, Febriyanti Panjaitan, Winarnie Winarnie, Hery Oktafiandi, Yohanes Yohanes

Abstract

Dropout mahasiswa menjadi persoalan penting dalam pendidikan tinggi vokasi karena berdampak pada keberlanjutan studi, efektivitas layanan akademik, dan mutu institusi. Penelitian ini bertujuan membangun model prediksi risiko dropout mahasiswa menggunakan pendekatan explainable machine learning. Dataset yang digunakan adalah Predict Students’ Dropout and Academic Success dari UCI Machine Learning Repository yang terdiri atas 4.424 data mahasiswa dengan atribut akademik, demografis, sosial-ekonomi, dan performa semester awal. Target asli tiga kelas diubah menjadi klasifikasi biner, yaitu dropout dan non-dropout. Model yang dibandingkan meliputi Logistic Regression, Random Forest, dan XGBoost. Evaluasi dilakukan menggunakan accuracy, precision, recall, F1-score, ROC-AUC, PR-AUC, confusion matrix, dan McNemar test. Interpretasi model dilakukan menggunakan permutation feature importance dan SHAP. Hasil penelitian menunjukkan bahwa XGBoost memperoleh performa deskriptif terbaik dengan accuracy 0,8859, F1-score kelas dropout 0,8250, dan ROC-AUC 0,9355. Namun, McNemar test menunjukkan perbedaan XGBoost dengan Logistic Regression tidak signifikan secara statistik. Fitur paling berpengaruh adalah jumlah mata kuliah semester kedua yang lulus, status pembayaran biaya kuliah, dan jumlah mata kuliah semester pertama yang lulus.

Keywords

dropout mahasiswa; explainable machine learning; XGBoost; SHAP; pendidikan tinggi vokasi

Full Text:

PDF

References

Andrade-Girón, D., Sandivar-Rosas, J., Marín-Rodriguez, W., Susanibar-Ramirez, E., Toro-Dextre, E., Ausejo-Sanchez, J., Villarreal-Torres, H., & Angeles-Morales, J. (2023). Predicting Student Dropout based on Machine learning and Deep Learning: A Systematic Review. EAI Endorsed Transactions on Scalable Information Systems, 10(5), 1–11. https://doi.org/10.4108/eetsis.3586

Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785

de Oliveira, C. F., Sobral, S. R., Ferreira, M. J., & Moreira, F. (2021). How does learning analytics contribute to prevent students’ dropout in higher education: A systematic literature review. Big Data and Cognitive Computing, 5(4). https://doi.org/10.3390/bdcc5040064

Fisher, A., Rudin, C., & Dominici, F. (2019). All models are wrong, but many are useful: Learning a variable’s importance by studying an entire class of prediction models simultaneously. Journal of Machine Learning Research, 20, 1–81. https://www.jmlr.org/papers/v20/18-760.html

Goran, R., Jovanovic, L., Bacanin, N., Stankovic, M. S., Simic, V., Antonijevic, M., & Zivkovic, M. (2024). Identifying and Understanding Student Dropouts Using Metaheuristic Optimized Classifiers and Explainable Artificial Intelligence Techniques. IEEE Access, 12(August), 122377–122400. https://doi.org/10.1109/ACCESS.2024.3446653

Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 2017-Decem(Section 2), 4766–4775. https://arxiv.org/abs/1705.07874

Martins, M. V., Baptista, L., Machado, J., & Realinho, V. (2023). Multi-Class Phased Prediction of Academic Performance and Dropout in Higher Education. Applied Sciences (Switzerland), 13(8). https://doi.org/10.3390/app13084702

Nagy, M., & Molontay, R. (2024). Interpretable Dropout Prediction: Towards XAI-Based Personalized Intervention. International Journal of Artificial Intelligence in Education, 34(2), 274–300. https://doi.org/10.1007/s40593-023-00331-8

Nti, I. K., & Ramanayake, S. (2026). Explainable machine learning for student dropout prediction and tailored interventions in online personalized education. Discover Artificial Intelligence, 6(1). https://doi.org/10.1007/s44163-026-01016-6

Rahmani, A. M., Groot, W., & Rahmani, H. (2024). Dropout in online higher education: a systematic literature review. International Journal of Educational Technology in Higher Education, 21(1). https://doi.org/10.1186/s41239-024-00450-9

Realinho, V., Machado, J., Baptista, L., & Martins, M. V. (2022). Predicting Student Dropout and Academic Success. Data, 7(11). https://doi.org/10.3390/data7110146

Tete, M. F., Sousa, M. de M., de Santana, T. S., & Fellipe, S. (2022). Predictive Models for Higher Education Dropout: A Systematic Literature Review. Education Policy Analysis Archives, 30(149), 1–23. https://doi.org/10.14507/EPAA.30.6845

Vaarma, M., & Li, H. (2024). Predicting student dropouts with machine learning: An empirical study in Finnish higher education. Technology in Society, 76(February), 102474. https://doi.org/10.1016/j.techsoc.2024.102474

Villar, A., & de Andrade, C. R. V. (2024). Supervised machine learning algorithms for predicting student dropout and academic success: a comparative study. Discover Artificial Intelligence, 4(1). https://doi.org/10.1007/s44163-023-00079-z

Wydra-Somaggio, G. (2021). Early termination of vocational training: dropout or stopout? Empirical Research in Vocational Education and Training, 13(1). https://doi.org/10.1186/s40461-021-00109-z

Yağcı, M. (2022). Educational data mining: prediction of students’ academic performance using machine learning algorithms. Smart Learning Environments, 9(1). https://doi.org/10.1186/s40561-022-00192-z

DOI: https://doi.org/10.20961/jiptek.v19i2.124459

Refbacks

  • There are currently no refbacks.