All Work

What Real Estate Listings Reveal About Who Applies for Mortgages

Shares of listings classified into different housing classes mapped against the share of low through upper-income mortgage applicants and the share of White and Black applicants in 2016.
Shares of listings classified into different housing classes (a–d) mapped against the share of low through upper-income mortgage applicants (f–i) and the share of White (e) and Black applicants (j) in 2016.
Expand Image
Close
Previous
Next
Shares of listings classified into different housing classes mapped against the share of low through upper-income mortgage applicants and the share of White and Black applicants in 2016.
Shares of listings classified into different housing classes (a–d) mapped against the share of low through upper-income mortgage applicants (f–i) and the share of White (e) and Black applicants (j) in 2016.

Team Lead

Areas

Related

Tags

Elizabeth Delmelle, Associate Professor and Program Director for the Master of Urban Spatial Analytics, recently published "How the marketing of real estate properties explains mortgage applicants by race and income" with Associate Professor Isabelle Nilsson from the University of North Carolina at Charlotte. The paper, published in Environment and Planning B: Urban Analytics and City Science, examines how property marketing language in real estate advertisements shapes the racial and income composition of mortgage applicants in neighborhoods. Using machine learning to analyze over 158,000 property listings and mortgage data from Charlotte, North Carolina (2001-2021), the researchers classified advertisements into five categories along a housing investment continuum. Their findings reveal stark racial disparities: Black applicants overwhelmingly apply for mortgages in neighborhoods where properties are marketed as "disinvested" with little profit-making potential, while White applicants concentrate in areas advertised as "expensive investments" or "new suburban" developments. These patterns persist even among similar income groups, suggesting that real estate marketing language serves as a subtle but powerful mechanism reinforcing residential segregation in American housing markets.