Date
Publisher
arXiv
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.
Study at a glance
- Question: Can privacy-preserving AI accurately predict which distance education students are at risk of dropping out?
- Setting and data: Distance education records from the large-scale OULAD dataset, covering early academic performance and digital engagement patterns.
- Method: Computational simulation comparing two machine learning models and data balancing techniques (Federated Learning).
Why it matters
Persistently high dropout rates in distance education remain a pressing institutional challenge. Addressing this requires proactively identifying at-risk students through early-warning systems while preserving data privacy and respecting student data sovereignty.
Key findings
- In distance education, privacy-protecting AI models achieve strong accuracy in identifying students at risk of dropping out.
- Decentralized AI is a practical, scalable early-warning solution that inherently protects student data privacy and ownership.
- Students' early academic performance and digital engagement patterns can effectively train decentralized systems to flag dropout risks.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who age?
Why use AI?
Study design
