Abstract
Financial distress is a state in which businesses struggle to pay their debts, whichfrequently results in bankruptcy or company failure. Small and medium-sizedenterprises are an essential part of economies, making substantial contributions toproductivity growth, innovation and employment. Evaluating financial health iscrucial to preventing possible hardship, reducing systemic risks and ensuring long-term stability because of its significant contribution to national and internationaleconomies.Bankruptcy prediction models play a critical role as early warning systems that enablefirms, lenders and policymakers to identify financial distress at an early stage and takecorrective action before failure becomes inevitable. These warning indicators mayresult from internal issues, such as decreasing profitability, declining liquidity orincreasing leverage, all of which are indicative of managerial and operationaldifficulties that may frequently be resolved with immediate attention.However, External factors such as interest rate movements and fluctuations in GDPcan significantly affect firms’ operating environments by increasing borrowing costs,suppressing demand and constraining access to finance.The small and medium-sized business bankruptcy prediction model created by Altmanand Sabato (2007) is revisited in this thesis, which proposed two models by addingaccounting and macroeconomic data. The study further evaluates the performance ofthe Altman and Sabato (2007) model by comparing results before and after theexclusion of the retained earnings-to-total assets variable. The investigation uses datafrom 2000 to 2018 and employs a variety of artificial intelligence techniques, such asdeep learning, machine learning algorithms, and ensemble methods.The results show that macroeconomic factors greatly improve bankruptcy models'forecast accuracy. Furthermore, the findings show that machine learning techniquestypically outperform deep learning methods in terms of accuracy. These findingsdemonstrate the importance of incorporating macroeconomic variables into credit riskassessment frameworks and have major implications for regulators, financialinstitutions, business decision-makers, and academic researchers.
Awarding Institution(s)
University of Plymouth
Supervisor
Peijie Wang, Alexander Haupt, Ahmed El-Masry
Document Type
Thesis
Publication Date
2026
Embargo Period
2026-03-05
Deposit Date
March 2026
Additional Links
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Recommended Citation
Badi, F. (2026) Predicting SMEs’ credit risk using artificial intelligence applications: Evidence from the UK SMEs. Thesis. University of Plymouth. Available at: https://doi.org/10.24382/p4pc-qb71
