Logo Lanfrica

Essilfie2005/EWS-MINI-PROJECT-

Domain:

education

Record type:

softwareproject
Creator:
Ess
Host:
An AI-powered Early Warning System (EWS) using XGBoost and Explainable AI (SHAP) to predict and prevent student dropout in West African university foundation programs. # Lightweight Dropout Prediction and Early Warning System (EWS) > **Explainable AI for University Foundation Programs in Ghana** > CS Department | 2026 Batch Mini-Project | Group 3 --- ## 🎯 Project Overview This system identifies at-risk foundation-year students by **Week 6 of semester** using only five registry-available features β€” no LMS telemetry, no paid cloud services. It combines an **XGBoost classifier** with **SHAP explainability** to give counsellors plain-language briefs on why a student was flagged, and logs all interventions for tracking. **AUC-ROC: 0.997** (XGBoost) vs 0.753 (Rule-based) on 2,000 student records. --- ## πŸ‘₯ Group Members | # | Index No. | Name | Role | |---|-----------|------|------| | 1 | 9019123 | Fobi Osei Randy Yamoah | ML / Data Engineer | | 2 | 9018323 | Angela Essein | Backend / Systems Dev | | 3 | 9019523 | Frank Fatawu Bakuwale Techi Junior | Frontend / Mobile Dev | | 4 | 9019323 | Fosu Kwame Korletey | Analytics / XAI Lead | | 5 | 9018623 | Essilfie David Amoabeng (PM) | EdTech / Pedagogy & PM | --- ## πŸ—οΈ System Architecture ``` University Registry (CSV) β”‚ β–Ό Python ETL Pipeline ←── CTGAN Synthetic Data (500 records) (SHA-256 anonymisation, feature engineering, imputation) β”‚ β–Ό SQLite Database (students, predictions, interventions, alerts) β”‚ β”œβ”€β”€β–Ί XGBoost Classifier (Optuna HPO) ──► Risk Score (0–1) β”‚ β”‚ β”‚ β–Ό β”‚ SHAP TreeExplainer ──► Waterfall Charts + Beeswarm β”‚ β–Ό FastAPI REST API (async, APScheduler nightly job) β”‚ β–Ό React Dashboard (university LAN, no internet required) β”œβ”€β”€ Risk Heatmap (cohort overview) β”œβ”€β”€ Student Drill-Down (SHAP waterfall) β”œβ”€β”€ Analytics Page (ROC curve, Beeswarm, Pilot Metrics) β”œβ”€β”€ Interventions Log └── Settings (upload data, re-train model) ``` **Deployment:** University server or Raspberry Pi 4 (8GB RAM). Zero paid cloud dependency. --- ## βš™οΈ Tech Stack | Component | Technology | Version | |-----------|-----------|---------| | Language | Python | 3.11.8 | | ML Classifier …

Languages

Licenses