Predicting SMEs’ credit risk using artificial intelligence applications: Evidence from the UK SMEs

Financial distress is a state in which businesses struggle to pay their debts, which<br/>frequently results in bankruptcy or company failure. Small and medium-sized<br/>enterprises are an essential part of economies, making substantial contributions to<br/>productivity growth, innovation and employment. Evaluating financial health is<br/>crucial to preventing possible hardship, reducing systemic risks and ensuring long-<br/>term stability because of its significant contribution to national and international<br/>economies.<br/>Bankruptcy prediction models play a critical role as early warning systems that enable<br/>firms, lenders and policymakers to identify financial distress at an early stage and take<br/>corrective action before failure becomes inevitable. These warning indicators may<br/>result from internal issues, such as decreasing profitability, declining liquidity or<br/>increasing leverage, all of which are indicative of managerial and operational<br/>difficulties that may frequently be resolved with immediate attention.<br/>However, External factors such as interest rate movements and fluctuations in GDP<br/>can significantly affect firms’ operating environments by increasing borrowing costs,<br/>suppressing demand and constraining access to finance.<br/>The small and medium-sized business bankruptcy prediction model created by Altman<br/>and Sabato (2007) is revisited in this thesis, which proposed two models by adding<br/>accounting and macroeconomic data. The study further evaluates the performance of<br/>the Altman and Sabato (2007) model by comparing results before and after the<br/>exclusion of the retained earnings-to-total assets variable. The investigation uses data<br/>from 2000 to 2018 and employs a variety of artificial intelligence techniques, such as<br/>deep learning, machine learning algorithms, and ensemble methods.<br/>The results show that macroeconomic factors greatly improve bankruptcy models'<br/>forecast accuracy. Furthermore, the findings show that machine learning techniques<br/>typically outperform deep learning methods in terms of accuracy. These findings<br/>demonstrate the importance of incorporating macroeconomic variables into credit risk<br/>assessment frameworks and have major implications for regulators, financial<br/>institutions, business decision-makers, and academic researchers.

Author dc:creator

• Badi, Fatima

Contributors dc:contributor

• Peijie Wang, Alexander Haupt, Ahmed El-Masry

Language dc:language

eng

Repository record dc:identifier

https://pearl.plymouth.ac.uk/pbs-theses/315

OAI identifier oai:identifier

oai:pearl.plymouth.ac.uk:pbs-theses-1314