Matt Franchi
@mfranchi.bsky.social
📤 28
📥 215
📝 3
computer science phd candidate @ cornell tech, nyc
https://mfranchi.net
reposted by
Matt Franchi
Gabriel Agostini
6 months ago
Migration data lets us study responses to environmental disasters, social change patterns, policy impacts, etc. But public data is too coarse, obscuring these important phenomena! We build MIGRATE: a dataset of yearly flows between 47 billion pairs of US Census Block Groups. 1/5
loading . . .
5
40
19
We’re releasing a new research dataset of 2.4 million street-level dashcam images, spanning all five boroughs of New York City from March-November 2020.
dataverse.harvard.edu/dataset.xhtml?…
loading . . .
Replication Data for: Detecting disparities in police deployments using dashcam data (FAccT'23)
A 10% random and anonymized sample of a dashcam image dataset spanning New York City limits during 2020.
https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/ZQ9GF0
over 1 year ago
0
1
0
Big thanks to @Gothamist for covering our recent policing work! Super cool to see commentary on the project from NYC community organizers and @dhadfieldmenell. Check it out here:
gothamist.com/news/nypd-does…
loading . . .
The NYPD doesn’t report where it deploys police. So scientists used AI, dashcams to find out.
Cornell Tech researchers used nearly 25 million rideshare dashcam images to identify police cars on city streets and areas that receive more attention than others.
https://gothamist.com/news/nypd-does-not-report-where-it-deploys-police-scientists-used-ai-dashcams-to-find-out
about 2 years ago
0
0
0
Excited to share our new paper, “Detecting disparities in police deployments using dashcam data”, accepted for publication at FAccT ‘23 (along with an exciting new dataset)! Joint work with @jdzamfi, @wendyju, and @2plus2make5.
#NYC
#NYPD
over 2 years ago
0
0
0
you reached the end!!
feeds!
log in
