Fraud detection in commercial banks in the U.S. is being transformed by artificial intelligence (AI), which identifies suspicious activity faster and more accurately, and minimizes financial losses. The conventional rule-based approaches are becoming insufficient to deal with the sophistication of the current fraudulent patterns, so AI-based methods like machine learning, deep learning, and natural language processing form a vital part of effective fraud prevention. This study evaluates the prospects and issues related to the use of AI in banking fraud detection. It examines the role of AI in the real-time detection of anomalies, in improving predictive analytics, and in improving adherence to regulatory frameworks. At the same time, it critically assesses issues such as algorithmic bias, data security, and the financial and operational implications of integrating AI systems into legacy infrastructures. By drawing on contemporary research and industry case studies, the paper contributes to a deeper understanding of how AI can be deployed responsibly to strengthen fraud prevention efforts while addressing the technical, ethical, and governance risks it presents.
CHUKWU et al. (Fri,) studied this question.