Air quality forecast dashboard in production

The brief

A city wants a public air-quality forecast that updates every morning. Build the forecast, then deploy it as a scheduled pipeline with an API and a public dashboard, data checks, versioned models and an alert when accuracy drops. Good looks like: a scheduled, tested pipeline, a live dashboard and API, and alerts that fire on real problems.

What you will build

1. Build and back-test the AQI forecast
2. Schedule daily data loading and checks
3. Serve forecasts from an API
4. Build a public dashboard
5. Monitor accuracy and data quality with alerts
6. Document how to retrain

Free, open data to build it with

• Air quality data in India ↗ Kaggle (CPCB data)

Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.