Data on housing affordability, built to support better decisions

My name is Levi Lebel, and I created this project to examine how rent burden, household income, and affordable housing activity vary across New York City.

Why this project

Housing costs shape where people can live, how much they can save, and how much financial security they have. A citywide average can hide large differences between neighborhoods. I wanted to see those differences at the ZIP-code level, and to set them next to the record of the City's affordable housing activity, so that patterns of need and patterns of investment can be examined side by side.

Research question

How do rent burden, household income and affordable housing activity vary across New York City's boroughs and ZIP codes, and where does high rent burden coincide with low affordable housing activity?

Data

• U.S. Census Bureau, American Community Survey (ACS) 2024 five-year estimates (survey years 2020–2024): Table B25070, gross rent as a share of household income (rent burden), and Table B19013, median household income, at the ZIP Code Tabulation Area level.
• NYC Department of Housing Preservation and Development (HPD), Affordable Housing Production by Building (NYC Open Data): affordable units counted in projects started from 2014 to mid-2026, covering new construction and preservation.
• Census 2020 ZCTA boundaries for the maps.

Every figure on the site is produced by a reproducible R pipeline and checked against the original data by an independent verification script. See the methodology and the full list of sources in the repository.

From coursework to portfolio project

The project began as university coursework in statistics: first a Brooklyn analysis, then a citywide analysis of all five boroughs. It has since developed into a broader portfolio project focused on data analysis, public policy and housing affordability. It now includes an interactive dashboard, documented statistical uncertainty, a validation pipeline and a scenario-based policy simulator. The research log records how each stage was added.

Analytical interests

• Business analytics
  Turning raw data into clear, decision-relevant metrics.
• Data visualization
  Designing charts and maps that are accurate, accessible and easy to read.
• Policy analysis
  Connecting evidence to real public policy questions, with careful attention to what the data can and cannot show.
• Data-driven decision-making
  Using transparent, reproducible analysis to support better decisions.

Explore

Start with the overview, try the policy simulator, or browse the source code on GitHub.