Case Study: Luxembourg National Railway Company (CFL) achieves smarter parking occupancy forecasting with Tryolabs

CFL forecasts parking occupancy up to 1 day ahead with Tryolabs in 1 week

The Luxembourg National Railway Company (CFL) faced the challenge of predicting the occupancy rate of two parking lots adjacent to its train stations to encourage commuter use. They required a custom machine learning model from Tryolabs that could provide these forecasts and integrate seamlessly into their existing in-house business analytics platform and workflow.

Tryolabs implemented two machine learning models for time-series prediction, a short-term and a long-term model, which were deployed directly on the client's infrastructure. The solution achieved an error rate of less than 5% in its predictions and had its first prototype running in production within one week, allowing CFL to provide real-time parking availability information to its passengers.

Luxembourg National Railway Company (CFL)