Evaluating Federated Learning for At-Risk Student Prediction: A Comparative Analysis of Model Complexity and Data Balancing
This provides a privacy-preserving solution for educational institutions to predict student dropout, though it appears incremental as it applies existing FL methods to a new domain with comparative analysis.
This study tackled the problem of high dropout rates in distance education by developing a Federated Learning framework to identify at-risk students while preserving data privacy, achieving strong predictive power with an ROC AUC of approximately 85%.
This study proposes and validates a Federated Learning (FL) framework to proactively identify at-risk students while preserving data privacy. Persistently high dropout rates in distance education remain a pressing institutional challenge. Using the large-scale OULAD dataset, we simulate a privacy-centric scenario where models are trained on early academic performance and digital engagement patterns. Our work investigates the practical trade-offs between model complexity (Logistic Regression vs. a Deep Neural Network) and the impact of local data balancing. The resulting federated model achieves strong predictive power (ROC AUC approximately 85%), demonstrating that FL is a practical and scalable solution for early-warning systems that inherently respects student data sovereignty.