Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fannie Mae Historical Loan Credit Performance Data #5

Open
lucaborella89 opened this issue Aug 27, 2024 · 1 comment
Open

Fannie Mae Historical Loan Credit Performance Data #5

lucaborella89 opened this issue Aug 27, 2024 · 1 comment

Comments

@lucaborella89
Copy link

lucaborella89 commented Aug 27, 2024

What dataset are you requesting?

US residential mortgage perforamance dataset from Fannie Mae Data Dynamics.

  1. Here the Multifamily dataset
  2. here the Single Family dataset

Is this open data?

No, currently available under Royalty-free data license

What is the use case for this dataset?

In the context of FINOS TechSprint 2024, the goal is to develop a proof-of-value (POV) for the business and proof-of-concept (POC) for the technological feasibility that simulates the effects of physical risk models and transition risk models on market risk and credit risk in trading activities, taking as the initial example a securitised portfolio of mortgages (MBS). More information here finos/traderX#191

Which organization produces the dataset?

Fannie Mae

Which format is the data in?

Refer to the links above

Which format would you like the data in?

TBD

How often does the data update?

Here the link to the refresh calendar

Who else would use this data ?

Mortgage Back Securities (MBS) are estimated to be around $10 to $12 trillion in total value. This data is relevant for banks, insurance companies and asset managers. The data can be used to build climate-focused applications and AI models, such as predictive and anomaly detection models, that can assess the climate risk exposure of borrowers more accurately. By analyzing patterns in loan repayments, borrower behavior, and climate-related factors (such as extreme weather events or carbon footprint), these models can identify early signs of financial distress driven by climate risks.

Other Comments

POC:

  • David Kelly (BIP) is TechSprint Use Case Project Lead
  • John Mark Walker (Fannie Mae) is FINOS AI Strategic Initiative Executive Sponsor

Others:
This issue is part of FINOS LLM Exploration Project and aims to validate the fit-for-purpose of OS-C Data Commons (and in particular Data Request) as "A comprehensive data contribution framework document that financial institutions can follow to contribute data securely and efficiently to an open financial dataset." More info here (slide 17)

@MichaelTiemannOSC
Copy link

Thanks for creating this record of interest. To set expectations, this data request form creates a potential work item that the OS-Climate community can prioritize, but the OS-Climate project does not make any promises that it will onboard the data.

@ericbroda copying in Eric Broda, who may have some advice on such data might be federated via the Data Bazaar. It would still require somebody to take ownership of doing the federation, but the Data Bazaar metadata and management might present a more favorable ROI equation than simplying trying to onboard the data without such structural/architectural support.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants