hmda

Build a harmonized DuckDB database from 40+ years of HMDA mortgage data (685M rows) in a single command.

HMDA mortgage lending disparity analyzer — denial rates, racial disparities, lending deserts, and lender benchmarking

Credit decisioning with model risk governance on 1.96M SBA loans and 93.4M HMDA applications. Ten promotion gates — one blocks my own model.

Independent model validation and AI governance framework for high-stakes financial decision models using public HMDA mortgage data.

Statistical lending-disparity screening for public HMDA data — a transparent, open-source screening tool for community advocates and journalists. Not an examination methodology

AI skills for NMTC eligibility, bank-CDFI peer benchmarking & HMDA analysis — grounded in audited PyPI tools, not hallucinated.

Orchestrated HMDA mortgage data pipeline using Apache Airflow — automated ingestion, cleaning, quality validation, and weekly model performance monitoring on 279K NC loan applications.

An interactive app that tells the story of the 2008 mortgage crisis and its decade-long aftermath through five borrowers, built on 64 million HMDA mortgage records (2007–2017) from the CFPB.

Can anyone still afford a home: a data story in eight chapters over 393 US metros, with a pre registered plan, a simulator with known truth, a dbt warehouse and a claim gate on every number

PySpark + Delta Lake lakehouse over 222.7M US mortgage records (HMDA 2018-2025): affordability, the 2022 rate hike, denials, fairness, and how much the government's own data changes between versions. Every number checked against official totals.

HMDA data analysis with Hadoop MapReduce and Apache Spark, reconstructed from an HPC/big-data course project with validated cross-framework results.

A simple, interpretable credit approval model built on HMDA data using decision trees

Analysis code for HMDA loan-level mortgage data and FFIEC Census files: lending disparities, tract-boundary corrections across vintages, longitudinal series, systemic-bank metrics, and a Python replication of published R methodology. Code-only; no data shipped.

Final Project for INFO 254 at UC Berkeley in Spring 2018

End-to-end mortgage approval analytics using Python, DuckDB, SQL, Tableau, and 3.8 million HMDA records.

Predicting VA loan approvals on 339K HMDA applications with ML, plus a two-stage fairness audit. M.S. Data Science capstone, Hawaii Pacific University.

Predicts U.S. home loan approvals using 4.25M real HMDA 2023 applications — XGBoost, Random Forest, Logistic Regression, ROC-AUC 0.9932

Tests HMDA mortgage records for differences in denial rates using several statistical methods, with an interactive dashboard.

Analyzing home mortgage data.

Mortgage denial-rate analysis (HMDA 2024) — Python + SQL + Tableau