NORMA eResearch @NCI Library

Machine Learning Frontiers in FinTech: Transforming Credit Risk Assessment

Mani, Emmanuel (2024) Machine Learning Frontiers in FinTech: Transforming Credit Risk Assessment. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (707kB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (226kB) | Preview

Abstract

In the fast-changing environment of FinTech, proper credit risk assessment will help reduce defaults and become more stable in a financial institution. This research will explain how the use of machine learning models in predicting credit risk can be done by utilizing a large dataset named the Lending Club dataset which contains extensive historical loan data of Lending Club, a peer-to-peer lending platform, obtained from Kaggle. It uses advanced techniques of data preprocessing and feature engineering in developing and evaluating various models, including Logistic Regression, Random Forest, Gradient Boosting Machine, and an ensemble model integrating several classifiers. The results presented herein show that the Random Forest model has the highest accuracy at 99.78% with an AUCROC of 0.9945, thus outperforming all other individual models and the ensemble model. Feature importance analysis indicates variables like recoveries, collection recovery fee, and FICO scores are strong predictors of credit risk. It also emphasizes the potential of machine learning in enhancing FinTech credit risk prediction ability, providing instructive information to the lender for the best possible decision that will reduce default risk. Moreover, these results underscore that proper choice of models should be made to ensure maximum predictive accuracy in the assessment of credit risk.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Byrne, Brian
UNSPECIFIED
Subjects: H Social Sciences > HG Finance > Credit. Debt. Loans.
H Social Sciences > HG Finance > Fintech
T Technology > T Technology (General) > Information Technology > Fintech
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in FinTech
Depositing User: Ciara O'Brien
Date Deposited: 05 Aug 2025 10:45
Last Modified: 05 Aug 2025 10:45
URI: https://norma.ncirl.ie/id/eprint/8426

Actions (login required)

View Item View Item