APPLYING MACHINE LEARNING FOR PREDICTING THE DROPOUT OF STUDENTS

Nông Thị Hoa

doi:10.34238/tnu-jst.12201

APPLYING MACHINE LEARNING FOR PREDICTING THE DROPOUT OF STUDENTS

About this article

Received: 04/03/25 Revised: 11/06/25 Published: 25/06/25

Authors

Nong Thi Hoa , Thuy Loi University

Abstract

Currently, the number of students dropping out of some universities is increasing due to many factors affecting students. Predicting the possibility of students dropping out will help to provide the supports for students in time. In this paper, the most new effective machine learning models were applied on the benchmark dataset to predict students dropping out. The benchmark dataset has 36 features about the learning results in the first two years and social factors. Important features were analyzed to improve the classification performance of machine learning models. The dataset was preprocessed to meet the input of each machine learning model. Neural network, Random Forest, Support Vector Machine were applied in this study. Parameters of each machine learning model were adjusted to get the highest classification accuracy. Experimental results show that Random Forest is the best machine learning model for the problem. Its accuracy reaches 91.33%.

Keywords

Neural network; Random Forest; Support Vector Machine; Machine Learning; Prediction

Full Text:

PDF (Tiếng Việt)

References

[1] M. Vaarma and H. Li, “Predicting student dropouts with machine learning: An empirical study in Finnish higher education, ” Technology in Society, vol. 76, pp. 1-10, 2024.

[2] A. Ridwana and A. M. Priyatnob, “Predict Students' Dropout and Academic Success with XGBoost,” Journal of Education and Computer Applications, vol. 1, no. 2, pp. 1-8, 2024

[3] A. Villar and C. R. V. de Andrade, “Supervised machine learning algorithms for predicting student dropout and academic success: a comparative study,” Discover Artificial Intelligence, vol. 4, no. 2, pp. 1-24, 2024.

[4] D. Arora, “Predicting Students Academic Success and Dropout Using Supervised Machine Learning,” International Journal of Scientific Study, vol. 11, no. 6, pp. 72-78, 2023.

[5] V. Realinho, J. Machado, L. Baptista, and M. V. Martins, “Predicting Student Dropout and Academic Success,” Data, vol. 7, no. 146, pp. 1-17, 2022.

[6] T. Purwoningsih, H. B. Santoso, K. A. Puspitasari, and Z. A. Hasibuan, “Early Prediction of Students’ Academic Achievement: Categorical Data from Fully Online Learning on Machine-Learning Classification Algorithms,” Journal of Hunan University (Natural Sciences), vol. 48, no. 9, pp. 131-141, 2021.

[7] L. U. M. Huynh, T. T. Pham, and V. N. Nguyen, “Predicting students' ability to graduate on time: a case study at Dong Thap University,” (in Vietnamese), Vietnam Journal of Education, vol. 24, no. 1, pp. 48-53, 2024.

[8] H. S. Luu, T. D. Tran, T. H. Nguyen, and T. N. Nguyen, “Predicting learning outcomes using deep learning techniques with multi-layered neural networks,” (in Vietnamese), Journal of Science, Can Tho University, vol. 56, no. 3A, pp. 20-28, 2020.

[9] L. T. N. Huynh and T. N. Nguyen, “Student learning outcome prediction system using open source recommender system library MYMEDIALITE,” (in Vietnamese), National Conference of Information Technology, 2013, pp. 20-28.

DOI: https://doi.org/10.34238/tnu-jst.12201

Refbacks

There are currently no refbacks.



Remember me