5. Machine learning for predicting the academic performance of lower secondary school students
Từ khóa:
Machine Learning; Academic performance; Lower secondary students; Prediction; Influencing factors.Tóm tắt
This study analyzes factors influencing academic performance among lower secondary school students and develops a Machine Learning-based predictive application. The dataset included 957 valid observations collected from students in Dong Nai Province, Vietnam. Reliability testing showed acceptable internal consistency, with Cronbach’s Alpha values ranging from 0.602 to 0.851. Exploratory Factor Analysis confirmed data suitability, with KMO = 0.915 and p < 0.001, and extracted seven representative factors. The regression results showed that the model explained 53.4% of the variance in academic performance, with the cognition-attitude-emotion factor having the strongest influence. Among nine predictive models, nonlinear models outperformed linear models. Random Forest and XGBoost achieved the highest R² value of 0.951, while SVR achieved R² = 0.899 and RMSE = 0.456. SVR was selected for deployment because of its balance between predictive accuracy, stability, and practical applicability. A web-based demo system was then developed to allow students to complete an online survey, receive predicted academic performance, and obtain learning recommendations. The findings demonstrate the feasibility of applying Machine Learning to academic support systems at the lower secondary level.
Tài liệu tham khảo
E. Alyahyan and D. Düştegör, “Predicting academic success in higher education: Literature review and best practices,” International Journal of Educational Technology in Higher Education, vol. 17, no. 1, pp. 1–21, 2020, doi: 10.1186/s41239-020-0177-7.
R. S. J. d. Baker and K. Yacef, “The state of educational data mining in 2009: A review and future visions,” Journal of Educational Data Mining, vol. 1, no. 1, pp. 3–17, 2009.
T. T. H. Duong, T. T. Nguyen, T. P. L. Tran, and T. H. G. Tran, “Exploring factors affecting Vietnamese students’ mathematical competence using PISA 2022 data: A machine learning approach with SHAP-based interpretation,” Journal of Education, vol. 25, no. 16, pp. 24–29, 2025.
D. Ifenthaler and J. Y. K. Yau, “Utilising learning analytics for study success: Reflections on current empirical findings,” Research and Practice in Technology Enhanced Learning, vol. 15, no. 1, pp. 1–17, 2020, doi: 10.1186/s41039-020-00129-y.
Ministry of Education and Training, Law on Education No. 43/2019/QH14. Hanoi, Vietnam, 2019.
Ministry of Education and Training, Circular No. 22/2021/TT-BGDĐT on the Assessment of Lower and Upper Secondary School Students. Hanoi, Vietnam, 2021.
N. L. Nguyen, “Predicting students’ academic performance using supervised machine learning models,” Equipment with New General Education Program, vol. 2, no. 93, pp. 5–7, 2023.
T. H. Nguyen, H. L. Tran, and T. K. Do, “Applying machine learning to identify influencing factors and predict students’ academic performance in blended learning models,” HNUE Journal of Science, vol. 68, no. 1, pp. 63–76, 2023.
T. K. S. Nguyen, H. H. Nguyen, T. T. T. Hoang, and Q. N. Tran, “Building a dataset of factors influencing academic performance of students at Hanoi Metropolitan University,” Journal of Science, vol. 82, pp. 29–43, 2024.
Z. Papamitsiou and A. A. Economides, “Learning analytics and educational data mining in practice: A systematic literature review of empirical evidence,” Computers & Education, vol. 67, pp. 49–64, 2014, doi: 10.1016/j.compedu.2013.02.004.
C. Romero and S. Ventura, “Educational data mining: A review of the state of the art,” IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 40, no. 6, pp. 601–618, 2010, doi: 10.1109/TSMCC.2010.2053532.
G. Siemens and R. S. J. d. Baker, “Learning analytics and educational data mining: Towards communication and collaboration,” in Proceedings of the 2nd International Conference on Learning Analytics and Knowledge, 2012, pp. 252–254, doi: 10.1145/2330601.2330661.
B. T. Tran, “Applying machine learning to predict students under academic warning at the University of Economics, Hue University,” Journal of Management and Economics, vol. 21, pp. 1–16, 2022.
