NYC Center for Innovation through Data Intelligence Government website / press release

Predicting Homeless Shelter Entry

NYC.gov

Ref: SRC-003-USA-001

https://www.nyc.gov/site/cidi/projects/predicting-homeless-shelter-entry.page

Accessed: 3/24/2026

Summary

Official CIDI project page describing partnership with NYU Furman Center to predict family shelter applications using ML on 2006-2015 administrative data. Reports predictions 20x better than random, 1.5x better than current prevention targeting. Key predictors include prior shelter applications, building history, and family assistance receipt.

View Harvard reference

NYC Center for Innovation through Data Intelligence (CIDI) (n.d.) 'Predicting Homeless Shelter Entry', NYC.gov. Available at: https://www.nyc.gov/site/cidi/projects/predicting-homeless-shelter-entry.page (Accessed: 24 March 2026).

Attached File

FILE

SRC-003-USA-001_Predicting_Homeless_Shelter_Entry.html 26 KB

Download

Linked Cases (1)

USA-001 USA Pilot / Controlled Trial Phase

Los Angeles County Homelessness Prevention Unit (HPU) Predictive Analytics

Social assistance Classical ML