Constantine Kontokosta
New York University, NY·Social Science
Where people go each day connects neighborhoods to one another. Those connections may help explain why some communities thrive while others fall behind.
- Fields
Social Science
Computer Science
Public Health & Epidemiology
- Topics
urban mobility
human mobility
smartphone mobility data
- Grants
- 1 known grant, last ended Oct 2026
What they work on
- Identify representativeness bias in smartphone mobility data, meaning which groups are over- or undercounted, and develop methods to correct it.
- Model neighborhood connectedness networks from mobility data covering 220,000 census blocks and analyze how their structure changes over time and in response to outside shocks.
- Define community and neighborhood boundaries from observed movement patterns between places, rather than relying on fixed administrative borders.
- Use community mobility networks with machine learning to predict neighborhood change and to measure integration and segregation between communities.
More about the research
This project asks how residents of different neighborhoods interact with other communities, how those interactions change over time and place, and how they differ with a neighborhood's income, race and other characteristics. It also asks whether patterns of connection are tied to community well-being and can signal neighborhood change.
Why it matters
Understanding how neighborhoods are connected through daily movement could give city planners, policymakers and community groups new indicators of segregation, integration and community well-being. Bias-corrected mobility measures and network-based predictions of neighborhood change could help target support to communities at risk of being left behind or displaced.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Mario Small
Columbia University, NY·Social Science
Build network-based measures of how well people are acquainted within and between zip codes, using data on acquaintance and contact ties, for all neighborhoods in the continental United States.
Guang Wang
Florida State University, FL·Computer Science
Build cross-domain data curation tools for MobilityNet that combine real mobility datasets from different sources to reduce data bias.
Elizabeth Roberto
Rice University, TX·Social Science·Early-career
Measure how road network connectivity relates to residential spatial variation and proximity to local public services across U.S. cities, using spatial and network analysis of road networks and demographic data.
The school
New York University: 72 labs on PI Pages, $1.5B a year on research, 540 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.