Integrating Data Mining, Statistics, and Machine Learning for Enhanced Credit Risk Scoring

Benzon, Donnal (2024) Integrating Data Mining, Statistics, and Machine Learning for Enhanced Credit Risk Scoring. Masters thesis, Dublin, National College of Ireland.

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

Abstract

The banking and financial services sector has transformed its credit risk assessment process through the fast-moving development of data analytics with machine learning and AI applications to determine borrowing capacity and set lending restrictions. Numerous machine learning algorithms such as XGBoost and CatBoost and HistGradientBoosting supplant traditional assessment tools because they deliver precise credit risk evaluations together with flexible adaptation and detailed analytics. This research examines credit risk assessment challenges that encompass predictive accuracy together with fairness requirements and regulatory standards. This research applies advanced algorithms together with explainable AI (XAI) methods SHAP and LIME to enhance model interpretation capabilities while establishing trust between stakeholders. The framework incorporates advanced predictive models in a single system which delivers fairness alongside ethical features to satisfy developing regulatory requirements and social norms. Through feature engineering combined with two-stage bias mitigation strategies applied during data preprocessing and model construction the research demonstrates pathways toward demographic group inclusivity. The framework shows practical use in financial reality through its ability to process data in real-time for largescale datasets. The proposed approach delivers enhanced predictive accuracy alongside transparency and fairness that allows financial institutions to maintain detailed social equity decision-making and accountably through scientific rigors which properly integrate technology with ethical and societal standards.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Shubhnil, Shubham 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 > Financial Services 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:	01 Sep 2025 15:08
Last Modified:	01 Sep 2025 15:08
URI:	https://norma.ncirl.ie/id/eprint/8681

Actions (login required)

View Item