Pandey, Shailesh Dayashankar (2024) Predicting Loan Defaults: A Machine Learning Approach Using Lending Club Data. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (555kB) | Preview |
Abstract
This research paper explores the application of advanced machine learning techniques for predicting borrower defaults in peer-to-peer (P2P) lending, a critical area for minimizing risk and enhancing the efficiency of lending platforms; with borrower behavior's increasing complexity and traditional credit-scoring models' limitations, our study aims to develop a robust credit-scoring framework utilizing methods such as XGBoost, Artificial Neural Networks (ANN), and Random Forest. Through comprehensive data preprocessing and feature selection, we identified key determinants of default risk and evaluated the performance of each model using metrics such as accuracy, precision, recall, and area under the ROC curve (AUC). Our findings reveal that while all models demonstrated strong predictive capabilities, XGBoost outperformed the others, significantly enhancing prediction accuracy. Additionally, ANN effectively captured complex patterns in the data, underscoring the importance of model selection in credit risk assessment. The implications of this research extend to improving decision-making processes for lenders, reducing information asymmetry, and fostering more reliable credit-scoring models. Future work is proposed to integrate alternative data sources and develop hybrid models, further advancing the field of credit risk assessment in the evolving fintech landscape.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Onwuegbuche, Faithful 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 11:41 |
Last Modified: | 05 Aug 2025 11:41 |
URI: | https://norma.ncirl.ie/id/eprint/8432 |
Actions (login required)
![]() |
View Item |