This is like an “early warning radar” for schools: it looks at student data and predicts which students are at risk of dropping out, while also explaining in plain terms why it thinks so (e.g., poor attendance, grades trend, engagement).
Educational institutions struggle to identify at-risk students early enough and to justify interventions with transparent reasoning. This work builds a predictive, explainable model to flag potential dropouts and show which factors drive that risk, helping target support and reduce attrition.
Classical-ML (Scikit/XGBoost)
Feature Store
Medium (Integration logic)
Data quality, feature engineering, and maintaining model performance across cohorts and institutions (concept drift)
Early Majority
Focus on explainability in addition to raw predictive accuracy, enabling educators and administrators to understand and trust why specific students are classified as at-risk, rather than relying on a black-box dropout model.