In the context of the digitalization of higher education, the analysis of student behavioral data has become a key instrument for improving the quality of education, personalizing learning trajectories, and enabling early detection of academic risks. However, centralized collection and processing of educational data create significant privacy threats, including personal data leaks, regulatory violations, and a decline in student trust. This study proposes a student behavior prediction model based on federated learning, ensuring data privacy while maintaining high predictive accuracy. The proposed architecture integrates federated aggregation mechanisms, differential privacy, and secure gradient exchange, enabling the construction of a distributed learning system without transferring raw data to a central server. A mathematical model of the student behavioral profile is developed, incorporating academic activity, digital traces in Learning Management Systems (LMS), temporal interaction patterns, and engagement indicators. The experimental component of the study includes simulations using both synthetic and real educational datasets, applying neural networks and gradient boosting within a federated learning environment. The results demonstrate that the federated model achieves comparable predictive accuracy to centralized training (with a difference of less than 2.3%), while significantly reducing the risk of personal data disclosure. Additional robustness analysis against gradient inversion attacks confirms an increased level of information protection. The findings support the feasibility of deploying federated learning in educational analytics systems and open new opportunities for developing ethically sustainable intelligent educational platforms. The practical value of the proposed approach lies in its ability to be integrated into existing Learning Management Systems (LMS) and national educational platforms. Under increasingly strict regulatory requirements regarding personal data processing, universities are compelled to adopt architectures that minimize the transmission of sensitive information. Federated learning enables inter-university analytics without the need for centralized data storage, significantly reducing legal and reputational risks.
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 (LAK), 2012, pp. 252-254.
R. Ferguson, “Learning analytics: Drivers, developments and challenges,” International Journal of Technology Enhanced Learning, vol. 4, no. 5-6, pp. 304-317, 2012.
C. Dwork, “Differential privacy,” in Proceedings of the 33rd International Colloquium on Automata, Languages and Programming (ICALP), 2006, pp. 1-12.
C. Dwork and A. Roth, “The algorithmic foundations of differential privacy,” Foundations and Trends in Theoretical Computer Science, vol. 9, no. 3-4, pp. 211-407, 2014.
European Parliament and Council of the European Union, “General Data Protection Regulation (GDPR),” Regulation (EU) 2016/679, 2016.
B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-efficient learning of deep networks from decentralized data,” in Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), 2017, pp. 1273-1282.
J. Konečný, H. B. McMahan, D. Ramage, and P. Richtárik, “Federated optimization: Distributed machine learning for on-device intelligence,” arXiv preprint arXiv:1610.02527, 2016.
Q. Yang, Y. Liu, T. Chen, and Y. Tong, “Federated machine learning: Concept and applications,” ACM Transactions on Intelligent Systems and Technology, vol. 10, no. 2, pp. 1-19, 2019.
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.
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, [Online]. Available: https://doi.org/10.1109/TSMCC.2010.2053532.
T. Li, A. K. Sahu, A. Talwalkar, and V. Smith, “Federated learning: Challenges, methods, and future directions,” IEEE Signal Processing Magazine, vol. 37, no. 3, pp. 50-60, 2020.
K. P. Murphy, Machine Learning: A Probabilistic Perspective, MIT Press, 2012.
T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, Springer, 2009.
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016.
S. Slade and P. Prinsloo, “Learning analytics: Ethical issues and dilemmas,” American Behavioral Scientist, vol. 57, no. 10, pp. 1510-1529, 2013.
L. Sweeney, “k-anonymity: A model for protecting privacy,” International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, vol. 10, no. 5, pp. 557-570, 2002.
L. Zhu, Z. Liu, and S. Han, “Deep leakage from gradients,” Advances in Neural Information Processing Systems (NeurIPS), vol. 32, 2019.
K. Bonawitz et al., “Practical secure aggregation for privacy-preserving machine learning,” in Proceedings of the ACM SIGSAC Conference on Computer and Communications Security, 2017, pp. 1175-1191.
V. Smith, C.-K. Chiang, M. Sanjabi, and A. Talwalkar, “Federated multi-task learning,” in Advances in Neural Information Processing Systems (NeurIPS), 2017.
N. Papernot et al., “Semi-supervised knowledge transfer for deep learning from private training data,” in International Conference on Learning Representations (ICLR), 2017.s
