How can AI-driven risk assessment models create personalized loan offers by effectively classifying applicants into risk categories

Kathrighatta Harish, Likith (2024) How can AI-driven risk assessment models create personalized loan offers by effectively classifying applicants into risk categories. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (535kB) | Preview
Preview	PDF (Configuration Manual) Download (734kB) | Preview

Abstract

In the evolving landscape of financial services, the importance of precise risk evaluation for loan applicants has grown significantly. Conventional methodologies, such as logistic regression and credit scoring, serve as foundational tools; however, they frequently overlook the intricate, nonlinear relationships present in contemporary financial datasets. This study investigates the role of artificial intelligence (AI) in refining risk assessment techniques, emphasizing how machine learning algorithms can facilitate the creation of customized loan proposals by accurately categorizing applicants into distinct risk groups. By harnessing recent innovations in AI, particularly ensemble techniques and gradient boosting, this research illustrates the shortcomings of traditional credit evaluation systems and highlights the capacity of AI to provide a more thorough assessment of borrower risk. A comprehensive analysis of various AI-based models—such as Random Forest, Gradient Boosting, and Logistic Regression—demonstrates the enhanced accuracy and flexibility of these approaches in comparison to their traditional counterparts. The results indicate that AI-driven models not only elevate the accuracy of risk evaluations but also support the development of personalized loan offers that align with individual financial circumstances. This tailored strategy not only boosts borrower satisfaction but also improves the efficiency of risk management. The paper emphasizes the revolutionary influence of AI on financial risk assessment and provides valuable insights into the adoption of advanced models for more informed lending practices.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Haque, Rejwanul UNSPECIFIED
Subjects:	H Social Sciences > HD Industries. Land use. Labor > HD61 Risk Management Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science 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
Depositing User:	Ciara O'Brien
Date Deposited:	18 Jun 2025 14:56
Last Modified:	18 Jun 2025 14:56
URI:	https://norma.ncirl.ie/id/eprint/7928

Actions (login required)

View Item