Overview

Extensive data on a portion of the mortgages acquired by Fannie Mae since year 2000 is accssible through Fannie Mae’s Data Dynamics portal. The first subsection below helps you get started with this dataset. The second section highlights the need to consolidate the data, which tracks each loan’s performance each month, into a one row per loan summary. The remaining sections provide samples of such consolidated loan data derived from Fannie Mae’s data.

• Fannie Mae’s Data
• Data Consolidation
• A One Year Sample
• A 10% Sample Covering All Years
• A Train / Test Split

If you need to work with the most detailed and recent mortgage data or if you wish to gain experience in manipulating large datasets then your best starting point is Fannie Mae’s data portal itself followed by Case Module 0: Data Pre-processing. However, if you wish to by-pass much of the data prep work then you will find that the consolidated data samples we have included here provide convenient on-ramps into your analysis.