Chapter 8: Artificial Intelligence Assisted Forecasting and Modeling Approaches in Finance Applications: Bankruptcy Prediction Models in the Banking Industry

Purpose: To investigate the impact of integrating artificial intelligence (AI) techniques, particularly deep learning, into bankruptcy prediction models within the banking sector.

Need for the study: With the historical development of bankruptcy prediction models, there is a growing recognition of the potential for AI to enhance the accuracy of these models. This study addresses the need to explore how AI can improve the prediction of financial failures in banks.

Methodology: Using data from banks spanning from 2020 to 2023, this study applies well-established bankruptcy prediction models including the Altman Z model, Altman Z’ model, Springate model, Zmijewski model, and Taffler model. Deep learning techniques are employed to teach these models to AI. Evaluation of the results is conducted using a majority voting decision-making system, incorporating algorithms such as KNN, naive Bayes, and decision trees.

Findings: Integrating AI techniques into bankruptcy prediction models has the potential to enhance the accuracy of forecasts. Evaluation criteria encompass both accuracy and precision, with promising results observed through the majority voting decision-making system. This study suggests a shift toward more sophisticated techniques for bankruptcy risk assessment within the banking sector.

Practical implications: Improved bankruptcy prediction models facilitated by AI techniques could enhance risk management strategies within banks, leading to more informed decision-making processes. This, in turn, could contribute to the overall stability and efficiency of the financial system. Moreover, the importance of considering contradictory results when applying AI-driven models in practice, highlighting areas for further research and refinement in the field of financial risk assessment.