Designing a Feedback-Driven Decision Support System for Dynamic Student Intervention
This work addresses the need for adaptive predictive models in education to enable timely academic interventions, though it is incremental as it builds on existing methods like LightGBM and SHAP.
The paper tackled the problem of static machine learning models in educational settings by proposing a Feedback-Driven Decision Support System with incremental retraining, resulting in a 10.7% reduction in RMSE after retraining and improved prediction accuracy for student interventions.
Accurate prediction of student performance is essential for enabling timely academic interventions. However, most machine learning models used in educational settings are static and lack the ability to adapt when new data such as post-intervention outcomes become available. To address this limitation, we propose a Feedback-Driven Decision Support System (DSS) with a closed-loop architecture that enables continuous model refinement. The system employs a LightGBM-based regressor with incremental retraining, allowing educators to input updated student performance data, which automatically triggers model updates. This adaptive mechanism enhances prediction accuracy by learning from real-world academic progress over time. The platform features a Flask-based web interface to support real-time interaction and integrates SHAP (SHapley Additive exPlanations) for model interpretability, ensuring transparency and trustworthiness in predictions. Experimental results demonstrate a 10.7% reduction in RMSE after retraining, with consistent upward adjustments in predicted scores for students who received interventions. By transforming static predictive models into self-improving systems, our approach advances educational analytics toward human-centered, data-driven, and responsive artificial intelligence. The framework is designed for seamless integration into Learning Management Systems (LMS) and institutional dashboards, facilitating practical deployment in real educational environments.