Comprehensive Analysis and Prediction of Loan Amount Distributions in the United States Mortgage Market

Mendbayar, Bolormaa (2024) Comprehensive Analysis and Prediction of Loan Amount Distributions in the United States Mortgage Market. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (3MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The 2022 Federal Financial Institutions Examination Council (FFIEC) Home Mortgage Disclosure Act (HMDA) dataset was analyzed to enhance financial risk assessment and decision-making in mortgage lending. Employed advanced data processing techniques such as shuffling and data chunking alongside exploratory data analysis (EDA) to uncover insights. Traditional methods, based on basic statistical techniques, offered limited insights into lending practices. Conducted a state-level analysis highlighted regional lending patterns and trends, identifying disparities and unique insights for localized strategies while demographic and financial factors visualized using Sankey diagrams revealed slight but not significant demographic bias. Random Forest was used for feature importance analysis, leading to the selection of the 20 most important variables, for developing ten predictive models including an ensemble approach. The ensemble method, which combined the three most accurate models—Random Forest, XGBoost, and CatBoost—proved to be the most effective, delivering the highest R-squared value and the lowest error metrics.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Alam, Naushad UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HG Finance > Banking H Social Sciences > HG Finance > Credit. Debt. Loans. Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	20 Aug 2025 10:30
Last Modified:	20 Aug 2025 10:30
URI:	https://norma.ncirl.ie/id/eprint/8588

Actions (login required)

View Item