This is like building several different “grade prediction calculators” for students, then comparing which one is best at forecasting who will do well or poorly so schools can intervene early.
Educational institutions struggle to identify at-risk students early enough to provide targeted support. This work compares multiple predictive models to find the most accurate way to forecast student performance from available data (e.g., demographics, attendance, prior scores), enabling data-driven interventions and resource allocation.
Classical-ML (Scikit/XGBoost)
Structured SQL
Medium (Integration logic)
Data Quality and Label Availability (requires clean historical student data and accurate outcome labels for reliable models)
Early Majority
Focuses specifically on systematically comparing multiple classical supervised learning algorithms for student performance prediction, helping institutions choose an empirically best-performing model rather than adopting a single technique by default.