Passenger and traffic flow prediction
Forecasts of crowding and traffic that help plan services and staffing.
The problem
Services and staff are planned on averages and struggle with peaks and events.
Data we need
- Ticketing or counter data
- Timetables and events
- Weather
How it works
- Assemble historical flow data
- Train prediction models by location and hour
- Validate against recent events
- Publish to planning tools
- Alert on unusual patterns
What it changes
Targets are agreed with you before we build, and measured on your data before release.
- Staff and services matched to demand
- Early warning of crowding
- Better event planning
Machine learning
Classification, regression and clustering models trained on your operational and business data.
- Gradient boosting
- Random forests
- Clustering