Fannie Mae Loan Performance Dataset
The Fannie Mae Loan Performance Dataset brings together detailed data on residential mortgages guaranteed by Fannie Mae in the United States. It makes it possible to analyze real estate credit trends and to model the risks of default.
Several million records, CSV format
Free access for research and analysis, with registration required on the official platform
Description
This dataset provides valuable information on:
- The characteristics of loans (amount, term, interest rate)
- Borrower profiles
- Refund schedules
- Events related to defaults, refinances, sales, or foreclosures
- The monthly performance of each loan
Thanks to its richness and granularity, it is used as a reference for studies on the American real estate market and credit risk assessment.
What is this dataset for?
The Fannie Mae Loan Performance Dataset is commonly used for:
- Training models for scoring and forecasting defaults
- Analysis of the stability of the mortgage market
- The evaluation of lending and securitization policies
- Academic research in economics, finance or data science
- Simulation of macroeconomic housing scenarios
Can it be enriched or improved?
Yes, in particular by:
- Combining data with macroeconomic indicators (rate, unemployment, real estate prices)
- Adding geographic data for regional analysis
- Calculating derived indicators such as Loan-to-Value or Debt-to-Income
- Integrating data into machine learning pipelines for predictive analytics
🔗 Source: Fannie Mae Loan Performance Dataset
Frequently Asked Questions
Can we identify the borrowers in this dataset?
No All personal data is anonymized to protect the privacy of borrowers.
Is the data updated regularly?
Yes, Fannie Mae releases monthly updates including new loan performance observations.
Does the dataset only cover compliant loans?
Yes, these are exclusively residential loans that meet Fannie Mae's criteria (premium, guaranteed, compliant with current regulations).
