International Journal of Education and Management Engineering (IJEME)
IJEME Vol. 16, No. 1, 8 Feb. 2026
Cover page and Table of Contents: PDF (size: 782KB)
Enhancing Student Performance Prediction with ANN-Based Transfer Learning
PDF (782KB), PP.21-33
Views: 0 Downloads: 0
Author(s)
Index Terms
Transfer Learning, Student Performance Prediction, Domain Shift, Artificial Neural Network (ANN), Higher Education Analytics
Abstract
Predicting student performance in higher education is challenging when data distributions differ across cohorts or programs. This paper proposes an adaptive transfer learning framework to improve prediction accuracy on a student dataset with simulated domain shifts. The dataset contains demographic, academic, and macroeconomic features for university students, with the target outcome indicating whether a student graduated, dropped out, or is still enrolled. We partition the data into distinct domains by academic program to emulate distributional differences. An Artificial Neural Network (ANN) model is first trained on a source domain and then fine-tuned on a target domain with a subset of layer weights frozen. We evaluate model performance using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R^2), comparing the proposed transfer learning approach against a baseline without transfer. The results show that transfer learning significantly improves prediction accuracy: RMSE and MAE are reduced while R^2 increases on the target domain, indicating better generalization. The findings demonstrate that an ANN-based transfer learning method can effectively mitigate domain shift in student performance prediction. This study presents the benefits of transfer learning in an educational context by using attribute-based domain separation, offering a practical approach for academic institutions to predict student outcomes across different programs or semesters.
Cite This Paper
Shoukath T. K., Midhun Chakkaravarthy, "Enhancing Student Performance Prediction with ANN-Based Transfer Learning", International Journal of Education and Management Engineering (IJEME), Vol.16, No.1, pp. 21-33, 2026. DOI:10.5815/ijeme.2026.01.02
Reference
[1]Behr, A., Giese, M., Teguim Kamdjou, H. D., & Theune, K. (2021). Motives for dropping out from higher education—an analysis of bachelor’s degree students in Germany. European Journal of Education, 56(3), 325-343.
[2]Kehm, B. M., Larsen, M. R., & Sommersel, H. B. (2020). Student dropout from universities in Europe: a review of empirical literature. Hungarian Educational Research Journal, 9(2), 147-164.
[3]Ramesh, V. A., Parkavi, P., & Ramar, K. (2013). Predicting student performance: a statistical and data mining approach. International Journal of Computer Applications, 63(8), 35-39.
[4]Durak, A., & Bulut, V. (2024). Classification- and prediction-based machine learning algorithms to predict students’ low and high programming performance. Computer Applications in Engineering Education, 32(1), e22679.
[5]Kukkar, A., Mohana, R., Sharma, A., & Nayyar, A. (2024). A novel methodology using RNN + LSTM + ML for predicting student’s academic performance. Education and Information Technologies, 29(11), 14403-14429.
[6]Manzali, Y., Akhiat, Y., Abdoulaye Barry, K., et al. (2024). Prediction of student performance using Random Forest combined with Naïve Bayes. The Computer Journal, 67(8), 2677-2689.
[7]Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345-1359.
[8]Tsiakmaki, M., Kostopoulos, G. K., Kotsiantis, S., & Ragos, O. (2020). Transfer learning from deep neural networks for predicting student performance. Applied Sciences, 10(6), 2145.
[9]Zhao, Y., Wang, P., & Wang, H. (2024). Improvement of applicability in student performance prediction based on transfer learning. Proceedings of the 5th International Conference on Artificial Intelligence in Education (AIEA 2024), 1-8.
[10]Namoun, A., & Alshanqiti, A. (2020). Predicting student performance using data mining and learning analytics techniques: a systematic literature review. Applied Sciences, 11(1), 237.
[11]Marcolino, M. R., Porto, T. R., Primo, T. T., et al. (2025). Student dropout prediction through machine learning optimization: insights from Moodle log data. Scientific Reports, 15(1), Article 9840.
[12]Akçapınar, G., Altun, A., & Aşkar, P. (2019). Using learning analytics to develop early-warning system for at-risk students. International Journal of Educational Technology in Higher Education, 16(40), 1-20.
[13]Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Proceedings of the 27th International Conference on Neural Information Processing Systems (NeurIPS), 3320–3328
[14]Li, S., Wei, G., & Zhao, Z. (2024). A method for predicting comprehensive grades of college students based on multi-model fusion. Control Engineering, 31(5), 475-482.
[15]Ma, Y., Chen, S., Ermon, S., et al. (2024). Transfer learning in environmental remote sensing. Remote Sensing of Environment, 301, 113924.
[16]Ampel, B. M., Samtani, S., Zhu, H., et al. (2024). Creating proactive cyber threat intelligence with hacker exploit labels: a deep transfer learning approach. MIS Quarterly, 48(1), 303–332.
[17]Shi, C., Wei, B., Wei, S., et al. (2021). A quantitative discriminant method of elbow point for the optimal number of clusters in clustering algorithm. EURASIP Journal on Wireless Communications and Networking, 2021(1), 1-16.
[18]Liu, H., Mao, M., Li, X., & Gao, J. (2025). Model interpretability in privacy-preserving student dropout prediction. PLoS ONE, 20(3), e0317726.
[19]Qiu, Y., Hui, Y., Zhao, P., et al. (2024). A novel image expression-driven modeling strategy for coke quality prediction in the smart cokemaking process. Energy, 294, 130866.
[20]Shoaib, L. A., Safii, S. H., Idris, N., et al. (2024). Utilizing decision tree models to map dental students’ preferred learning styles with suitable instructional strategies. BMC Medical Education, 24(1), 58.