Scalable ETL pipeline and Machine Learning model to predict mortgage defaults using Freddie Mac’s Single-Family Loan-Level Dataset. Migrated from a Pandas-based legacy system to a distributed PySpark architecture on Databricks to handle multi-gigabyte time-series performance data.
Notebook project scraping and organizing mortgage loan-rate data.
ELT pipeline and Postgres warehouse for the public HMDA mortgage data. Loads 23.7 million loan records across 2023 and 2024 through bronze, silver and gold layers, with fifteen quality gates.
MCP server for FinanceRateCalc — query lender-level FHA denial statistics from the complete 2025 federal HMDA record. Historical observations, never individual predictions.
CoreLogic — rebranded as Cotality in 2025 — is a property data and analytics company providing real estate, mortgage, tax, hazard, and climate-risk information across approximately 99% of U.S. residential properties plus operations in Australia, New Zealand, the United Kingdom, Canada, Germany, and India.
Add a description, image, and links to the mortgage-data topic page so that developers can more easily learn about it.
To associate your repository with the mortgage-data topic, visit your repo's landing page and select "manage topics."