EXPLORING THE ROLE OF ARTIFICIAL INTELLIGENCE IN MANAGING EMERGING RISKS: AN IN-DEPTH STUDY OF AI APPLICATIONS IN FINANCIAL INSTITUTIONS' RISK FRAMEWORKS

This research focuses on using approaches such as ML and ANNs in FRM while will look at and try to analyze their effectiveness compared to logistic regression, random forest, and support vector machine. Training and testing of the models were done using accuracy, precision, recall and F1-score with a sample database comprising of 15000 financial records. Imputation of missing values; selection of informative variables; and data scaling, were performed to enhance the reliability of the models used. Analysis of the results revealed that ANNs and more so DNNs surpassed conventional approaches in the prediction of financial risks. Still, the integration of traditional and AI-based approaches resulted in improved performance outcomes as well as proved to be more resilient to multiple risk factors. Thus, the work concludes that the enhancement of the integration of AI in the management of financial risk can enhance the accuracy of risk assessment. The future work should include improvements regarding the interpretability of the model, testing on a more substantial number of data and experimenting with reinforcement learning to apply it to decision making in the financial risk cases.