Essays in financial technology: banking efficiency and application of machine learning models in Supply Chain Finance and credit risk assessment

Li, Yixuan (2024) Essays in financial technology: banking efficiency and application of machine learning models in Supply Chain Finance and credit risk assessment. PhD thesis, University of Glasgow.

Full text available as:
[thumbnail of 2023LiYixuanPhD.pdf] PDF
Download (4MB)


The financial landscape is undergoing a significant transformation, driven by technological innovations that are reshaping traditional banking practices. This thesis examines the evolving relationship between financial technology (FinTech) and banking, specifically addressing the credit risk aspects within the domains of Supply Chain Finance (SCF) and peer-to-peer (P2P) lending.

FinTech has experienced rapid growth and innovation over the past decade. It encompasses a wide range of technologies and services that aim to enhance and streamline financial processes, disrupt traditional banking models, and offer new solutions to consumers and businesses. The status of FinTech and banking is assessed through an extensive review of the current literature and empirical data. Accordingly, FinTech development has significantly impacted the financial landscape, driving innovation, competition, and customer expectations while it has exposed inefficiencies within traditional banking, it has also compelled banks to evolve and embrace technological advancements. The impact of FinTech on traditional banking models, customer behaviours, and market competition is aimed to be explored. This investigation highlights the challenges and opportunities that arise as FinTech disrupts and reshapes the banking sector, emphasizing its potential to enhance efficiency, accessibility, and customer experiences. As Chapter 3 focuses on an empirical analysis of the impact of FinTech on the operating efficiency of commercial banks in China.

Further, in the context of credit risk, the thesis focuses on SCF and P2P lending, two prominent areas influenced by FinTech innovation. SCF has witnessed substantial transformation with the infusion of FinTech solutions. Digital platforms have streamlined the flow of funds within complex supply networks, enhancing the liquidity of suppliers and optimizing working capital for buyers. However, this transformation introduces new credit risk challenges. As suppliers' financial data becomes more accessible, the need for accurate risk assessment and predictive modelling becomes paramount. The integration of big data analytics, machine learning, and artificial intelligence (AI) holds the promise of refining credit risk evaluation by offering real-time insights into supplier financial health, thereby improving lending decisions and reducing defaults.

Similarly, P2P lending has redefined the borrowing and lending landscape, enabling direct connections between individual borrowers and lenders. While P2P lending platforms offer speed, convenience, and access to credit for previously underserved segments, they also grapple with credit risk concerns. Evaluating the creditworthiness of individual borrowers without sufficient credit history demands innovative risk assessment methodologies. The emergence of data issues, such as imbalanced data issues, feature selection, and data processing, presents challenges in building accurate credit risk profiles for P2P lending participants. FinTech solutions play a pivotal role in creating and implementing these alternative risk assessment models. Note that, few studies in the literature investigate the benchmark of the advanced method of solving the credit risk assessment in emerging financial services.

This thesis aims to address this research gap by evaluating the effectiveness of credit risk assessment models in these FinTech-driven contexts, considering both traditional methodologies and novel data-driven approaches. Chapter 4 investigates the credit risk assessment issue in Digital Supply Chain Finance (DSCF) with the Machine Learning approach and Chapter 5 emphasises the issue of data imbalance of credit risk assessment in P2P Lending.

By addressing these gaps and issues, this thesis aims to contribute to the broader discourse on FinTech's role in shaping the future of banking. The findings have implications for financial institutions, policymakers, and regulators seeking to harness the benefits of FinTech while mitigating associated risks. Ultimately, this study offers insights into navigating the evolving landscape of credit risk in SCF and P2P lending within the context of an increasingly technology-driven financial ecosystem.

Item Type: Thesis (PhD)
Qualification Level: Doctoral
Subjects: H Social Sciences > HG Finance
Colleges/Schools: College of Social Sciences > Adam Smith Business School
Supervisor's Name: Stasinakis, Professor Charalampos and Yeo, Dr. WeeMeng
Date of Award: 2024
Depositing User: Theses Team
Unique ID: glathesis:2024-84159
Copyright: Copyright of this thesis is held by the author.
Date Deposited: 26 Mar 2024 15:02
Last Modified: 26 Mar 2024 15:05
Thesis DOI: 10.5525/gla.thesis.84159

Actions (login required)

View Item View Item


Downloads per month over past year