<![CDATA[The prediction of financial distress in the banking sector has become increasingly critical amid rising digital risks, managerial failures, and regulatory pressures, particularly during the 2020–2024 period. This study aims to analyze the methods used for predicting financial distress in the banking sector through a systematic literature review. Using a qualitative approach and a descriptive-analytical literature study method, this research examines scholarly articles from reputable sources. The analysis reveals that while traditional models such as the Altman Z-Score and CAMELS are still in use, AI/ML-based models such as Random Forest and Long Short-Term Memory (LSTM) are gaining prominence due to their higher accuracy. However, the adoption of predictive technologies remains limited in developing countries due to data and resource constraints. This study underscores the importance of developing predictive frameworks that are responsive to digital disruption and integrate ESG factors, while also addressing the research gap concerning the application of Generative AI in banking. The findings are expected to offer valuable insights for regulators and practitioners in anticipating financial crises more proactively.]]>
Copyrights © 2025
