Leveraging Alternative Data and Machine Learning for Inclusive Credit Scoring

Mureithi, Rose Edith Wairimu (2025) Leveraging Alternative Data and Machine Learning for Inclusive Credit Scoring. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (732kB) | Preview
Preview	PDF (Configuration Manual) Download (320kB) | Preview

Abstract

This research investigates the potential of integrating alternative data with machine learning (ML) to create a more inclusive credit framework for underserved populations. The point-based, traditional credit scoring system has little or no opportunity to assess individuals with thin credit files, thus causing them financial exclusion. This research uses a huge peer-to-peer lending marketplace dataset for developing and comparing ML models on the basis of traditional, alternative, and blended data features. Findings confirm that the models integrated with alternative data outrank the conventional metrics models. Multiple ML models, i.e., Logistic Regression, Random Forest, and XGBoost, have been used in the study and have utilized SHAP (SHapley Additive exPlanations) to make the model interpretable. The results indicate that a hybrid model using conventional and alternative data yields a more accurate and fairer assessment of credit risk and hence greater financial inclusion. This study offers valuable insights for financial institutions and policymakers who are seeking to develop fairer and more effective credit scoring systems.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Byrne, Brian UNSPECIFIED
Uncontrolled Keywords:	Credit Scoring; Alternative Data; Machine Learning; Model Interpretability; Financial Inclusion; Hybrid Model
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:	20 Aug 2026 09:22
Last Modified:	20 Aug 2026 09:22
URI:	https://norma.ncirl.ie/id/eprint/9558

Actions (login required)

View Item