Data Science
Air Quality Prediction
Data Scientist & ML Engineer
Developed a comprehensive air quality prediction platform powered by ensemble learning, sensor data ingestion, and a lightweight API surface. Delivered 94% accuracy and automated alerts for city planners.
View live project ↗Challenge
Municipal planners needed to anticipate pollution events fast enough to warn residents and adjust traffic flows.
Approach
Built an ensemble forecasting pipeline that cleanses multi-source sensor data, engineers weather features, and serves predictions through a containerised API.
Outcome
Delivered 94% accurate forecasts powering daily dashboards and automated alerts across three city districts.
Highlights
- 94% accuracy across 7-day forecasts
- Streaming architecture with sub-second responses
- Interactive dashboards for non-technical teams