At Polygon Research, every insight we deliver is built upon the most comprehensive, granular, and rigorously processed open data in mortgage and housing finance.
.svg)
.png)
In housing finance, true insight isn't found in summaries - it's in the details of every single transaction. We meticulously model microdata at the loan-level. Microdata is the DNA and the backbone of our market intelligence.
It means we go beyond dashboards to capture the complete story: every borrower, every lender, every property, every financial nuance, directly from the source. From 124+ million records in HMDAVision to millions of FHA endorsements and billions of Agency RMBS transactions, we transform vast datasets into a singular, high-fidelity view of the market. Even with complex sources like Census PUMS data, we leverage microdata for unprecedented speed and depth in demographic insights.
This granular precision is your ultimate advantage. Lists and tables are built with assumptions that may have nothing to do with your market and market position. We model the microdata that illustrates individual behaviors so you can understand the trends. It allows us to build powerful dashboards for instant analysis, but it's the underlying loan-level truth that empowers your AI and strategic decisions with unmatched clarity and foresight.
We model loan-level and microdata in the interactive dashboards of Polygon Vision and Polygon Pulse.
Discover patterns and trends in your data effortlessly. Visualise historical data to forecast future performance.
Dive deeper into your data with interactive charts. Hover and click for more detailed insights and breakdowns.
Dive deeper into your data with interactive charts. Hover and click for more detailed insights and breakdowns.
Answers to questions about our key data sources.
HMDA LAR stands for Home Mortgage Disclosure Act Loan Application Register. It is the leading public source of U.S. mortgage lending data. Mandated by the 1975 HMDA and Regulation C, it captures loan-level details from banks, credit unions, and lenders on mortgage applications, originations, and denials. Overseen by the Consumer Financial Protection Bureau (CFPB), the data is collected annually and updated by CFPB weekly for any corrections filed by lenders. HMDA LAR is privacy-protected, and released publicly by March of the following year.
Polygon Research champions open data. We source HMDA LAR transparently, validate it for reliability, and adhere to CFPB and FFIEC privacy protections. HMDA LAR illuminates the mortgage market, promoting fairness and opportunity in housing.
Millions of annual LAR records. We model 2018-2024 (124+ million records).
Applicant Demographics: Race, ethnicity, gender, income.
Loan Details: Amount, type (e.g., home purchase, refinance), status (e.g., originated, denied), amortization type (Fixed vs Adjustable), HELOC, Lien Status, Reverse Mortgage and more.
Property Info: Location (state, MSA, county, census tract, zip code), property type & appraised or sales value (whichever is lower).
Lender Data: Institution name (and LEI), type, loan channel, size, secondary market strategy.
Loan Pricing: Interest rate, Discount points, Lender Credits, Origination Charges, Total Loan Costs, DTI, CLTV, Loan Amount.
The ACS Public Use Microdata Sample (PUMS) provides an unparalleled depth of detail at the individual and household level. Unlike aggregated data, PUMS allows Polygon Research's users to analyze raw, anonymized survey responses on household characteristics such as household size, composition, tenure (owner/renter), and housing costs. In addition, ACS PUMS allows for individual demographics analysis - for example, age, sex, race, ethnicity, educational attainment, employment status, and income. While anonymized, PUMS data offers sufficient geographic detail at a neighborhood level (Public Use Microdata Areas - PUMAs) for meaningfull analysis.
Polygon Research simplifies the complexity of ACS PUMS data, representing over 334 million people and 131 million households, by streamlining data processing. We expertly acquire, clean, normalize, and apply statistical weights to ensure accurate, representative insights. In parallel, we deliver intuitive tools. For example, our Polygon Vision suite offers user-friendly interfaces to filter, visualize, and analyze data for specific demographic and socio-economic groups - from national, state, MSA, county and all the way to neighborhood level.
Polygon Research harnesses loan-level data from Fannie Mae, Freddie Mac, and Ginnie Mae to deliver powerful insights into the U.S. mortgage market, enabling data-driven strategies. We expertly process loan-level data from all three agencies, with Ginnie Mae’s data seamlessly integrated alongside Fannie Mae and Freddie Mac’s. We ensure accuracy and strict adherence to all applicable guidelines for each agency.