- F1 0.92 · 95.2%
- Sprint Risk
- MAE 0.8 · R² 0.89
- Effort Est.
- F1 0.93 · 97.1%
- Burnout
Overview
An ML-driven MERN platform that predicts sprint-failure risk, auto-estimates task effort, and flags developer burnout before it crosses critical thresholds.
Three XGBoost models served via a FastAPI microservice, trained on IEEE TSE benchmark datasets with SMOTE + Optuna hyperparameter optimization.
Replaces manual sprint planning with data-driven forecasts surfaced live in the dashboard.
Tech stack
- Python
- XGBoost
- FastAPI
- Scikit-learn
- Optuna
- React
- Node.js
- MongoDB
- Socket.io
- Docker
Screens & results
