Abstract

When the pandemic hit the world, Västtrafik wanted a precise way to inform travelers about what trips were likely to be crowded so they could plan their trips safely. Since Västtrafik works in a large geographical area with a heterogeneous population landscape, creating warnings based only on the time of day wasn't considered good enough. We will present a use case of machine learning in production based on data from the automatic passenger counting system. The focus will be on all those details that make ML solutions useful in real life. How do you communicate the results? How do you maintain it? What engine does the model use? We will also present results on how travelers received it and how it is continuously evaluated and evolving today.

Björn Thalén

Data Scientist @ Västtrafik

Björn Thalén is a data science consultant at B3Indes, a company helping organizations to create value from data. At one of his clients, Västtrafik, Björn has been the lead developer for an AI model for crowd predictions. His academic background is in applied mathematics and the history of science. In his professional life, he has focused on mathematical optimization and transportation planning systems, helping some of the world's leading transportation companies to optimize their planning. Björn is a coordinator for the EURO Practitioners' Forum, a European network of industry mathematicians. He got his MSc at Linköping University and has lived in Gothenburg since 2010.