Introduction
GVB stands for Gastvrij (Hospitable), Verbindend (Connecting) and Betrouwbaar (Reliable).
These are the core values with which the employees of GVB provide public transport in Amsterdam and its surroundings.
GVB ensures that the city of Amsterdam is accessible to everyone.
With approximately 5,000 employees, temporary workers and externals, they are among the largest employers in Amsterdam – and among the five best employers in Amsterdam.
Customer
GVB
Tools/Techniques
Databricks, Azure DevOps
Services
Data Science & AI
Industry
Public Transport
The goal-driven data solution
With the segmentation model based on travel behavior, GVB gains better insights into how passengers move. This enables GVB to offer suitable travel products, for example. The segmentation model needs to stay up to date with developments over the years. It is important that the model is implemented robustly to meet GVB’s data architecture standards.
We have established a uniform and robust MLOps lifecycle. This is crucial for effectively deploying and maintaining the segmentation model in production. We have set up an MLOps workflow in Databricks, with various reusable templates.
“It was very interesting to improve the Databricks workflow for Machine Learning projects by setting up a robust MLOps lifecycle. This has laid a solid foundation for future projects to be structured in a similar manner.”
Check out other case studies,
