What is it about?
Cities with universities often struggle to understand how students affect daily life, traffic, and housing. Students move differently than the general population, but cities rarely have detailed data tracking where students live or how they commute. This paper offers a creative solution to that data gap. The research, based at Ghent University, works in two steps. First, it estimates where students likely live across a city, even without detailed housing records. It does this by looking at factors that typically attract student renters, such as how close a location is to university campuses, the city center, and train stations. By combining these clues with limited survey data, the method can produce a realistic map of student housing across an entire city. Second, using these estimated home locations alongside real class schedules, the researchers built a computer simulation that mimics individual students' daily journeys, deciding when they go to class, take breaks, head home, or travel to family on weekends, and which transportation they use. Tested on Ghent, Belgium, the approach closely matched real housing survey data and successfully recreated realistic daily movement patterns, such as crowds building up near campuses during class hours.
Featured Image
Photo by Dmitrii E. on Unsplash
Why is it important?
Student mobility is for many cities still a blind spot. This kind of tool could help city planners make smarter decisions about public transportation schedules, bike lanes, and housing policy, all while protecting student privacy, since it doesn't rely on tracking individuals directly. It also lays groundwork for similar tools studying other groups with predictable routines.
Perspectives
This article grew from my own experiences in Ghent, a city shaped by its large student population. What started as a simple question—where are students and how do they move through the city?—quickly revealed a major blind spot for both the city and the university. I hope this work shows that even with limited data, we can still generate meaningful insights to support better urban planning and decision-making.
Quinten van de Korput
Ghent University
Read the Original
This page is a summary of: From Static Data to Dynamic Mobility: A Spatio-Temporal Method for Student Mobility Estimation, March 2026, ACM (Association for Computing Machinery),
DOI: 10.1145/3748522.3779825.
You can read the full text:
Contributors
The following have contributed to this page
