Artificial Intelligence Driven Personalized Loan Pricing in Peer to Peer Lending Finance

Patel, Parth (2024) Artificial Intelligence Driven Personalized Loan Pricing in Peer to Peer Lending Finance. Masters thesis, Dublin, National College of Ireland.

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

Abstract

This study analyses the use of AI in creating individualized loan pricing models for peer-to-peer (P2P) lending platforms, using the Lending Club Corporation dataset, and solving problems in credit risk management, borrower-lender linearisation and transparency, and financial inclusion. AI-driven data processing can boost the creation of individualized loan pricing models and allow for risk stratification of borrowers by adding extra insights to lenders and thus ameliorate performance. The dataset was pretreated and had the following techniques for preprocessing steps, such as oversampling to counteract class imbalance and feature importance analysis to detect the main predictor variables affecting the study of creditworthiness. The research used a broad range of methods that include Logistic Regression, Random Forest, Gradient Boosting, and Neural Networks to estimate the default probabilities and develop more elaborate loan pricing plans. The effectiveness of displayed high Neural Networks has been found to be a 92% accuracy rate and 95% recall due to the method’s ability to precisely distinguish high-risk borrowers. The AI-powered personalized pricing schemes grounded in these models were very successful in this regard and therefore, it is possible to set competitive interest rates while reducing risks, and thus contribute to fair lending practices. Through Lending Club’s realistic dataset, the research conducts a comprehensive study of the potential of AI to solve the real-world problems that are caused by the P2P lending platforms. In addition, the article expounds on the bigger issues such as the use of power for the development of people without banking services and on ethical issues of data privacy and algorithms. The research is bringing newness to P2P lending ecosystems and thus the creation of a scalable and data-driven framework for personalized loan pricing, which is a breakthrough in financial technology and is a new definition of the traditional lending practices.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Cosgrave, Noel UNSPECIFIED
Subjects:	H Social Sciences > HG Finance 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.
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	04 Sep 2025 08:51
Last Modified:	04 Sep 2025 08:51
URI:	https://norma.ncirl.ie/id/eprint/8768

Actions (login required)

View Item