Trustworthy AI for Financial Services: An Ethical Framework and Explainability-Driven Compliance in Credit Risk Modelling

Ibiwoye, Ayotomiwa Agboola (2025) Trustworthy AI for Financial Services: An Ethical Framework and Explainability-Driven Compliance in Credit Risk Modelling. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (501kB) | Preview
Preview	PDF (Configuration Manual) Download (936kB) | Preview

Abstract

Artificial intelligence (AI) is increasingly central to financial decision-making, especially in high-risk applications like credit scoring. However, the lack of transparency of many AI systems raises significant ethical, regulatory, and operational concerns. This dissertation develops and proposes a dual-layer solution: a machine learning artefact—“TrustScore”—designed to predict creditworthiness using Random Forests and SHAP explainability, and an accompanying ethical governance framework aligned with the GDPR and the EU AI Act. By embedding transparency, fairness, and accountability into the AI lifecycle, the artefact ensures regulatory compliance and operational reliability. Evaluation on a synthetic dataset demonstrates high accuracy (85.1%) and interpretability, with fairness metrics confirming ethical robustness. The ethical framework draws from IEEE standards, OECD principles, and ISO/IEC 42001 to ensure governance at every lifecycle phase. This project offers a replicable model for deploying high-risk AI in finance that is not only performant but also explainable, compliant, and trustworthy by design.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Del Rosal, Victor UNSPECIFIED
Uncontrolled Keywords:	AI Governance; Credit Scoring; Explainable AI (XAI); GDPR; EU AI Act; SHAP; Trustworthy AI; Financial Compliance; Algorithmic Fairness
Subjects:	H Social Sciences > HD Industries. Land use. Labor > HD61 Risk Management Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence H Social Sciences > HG Finance > Credit. Debt. Loans. H Social Sciences > HG Finance > Financial Services
Divisions:	School of Computing > Master of Science in Artificial Intelligence for Business
Depositing User:	Ciara O'Brien
Date Deposited:	24 Aug 2026 10:20
Last Modified:	24 Aug 2026 10:20
URI:	https://norma.ncirl.ie/id/eprint/9588

Actions (login required)

View Item