Traceback analyzes learning signals to identify why each student is struggling — and generates a personalized recovery plan.
Enter a student ID to view their signals, root cause diagnosis, and personalized learning plan.
A full machine learning pipeline built on the OULAD dataset to diagnose student learning problems and generate personalized interventions.
7 OULAD CSV files cleaned and merged into a master table of 28,785 students × 32 columns.
10 signals normalized. 3 composite risk scores built: academic_risk, engagement_risk, persistence_risk.
XGBoost classifier trained on 13 features. 92.5% accuracy across 5 root cause categories.
Rule-based engine generates 4-step personalized plans using each student's real signal values.
Student barely interacts with the platform. Attendance problem, not knowledge.
Engaging but scoring low despite effort. Foundational concept is missing.
Was performing OK but scores are dropping. Something changed recently.
Good coursework scores but poor exam performance. Performance-under-pressure issue.
Consistently near but below threshold. Small targeted push needed.
Built entirely in Python on Google Colab using open-source libraries and the OULAD dataset.