Abstract

This study investigates the role of machine learning (ML) in enhancing banking efficiency, focusing on credit risk assessment, fraud detection, and customer segmentation. By employing various ML models, including gradient boosting, neural networks, and clustering techniques, the study demonstrates how ML-based financial technology (FinTech) solutions optimize decision-making and streamline banking operations. Findings indicate that ML models outperform traditional methods in predictive accuracy, especially in managing credit risk and detecting fraudulent transactions. Clustering techniques provide valuable insights for customer segmentation, enabling banks to implement targeted marketing strategies. However, challenges such as data privacy, regulatory compliance, and model interpretability underscore the need for a balanced approach to ML adoption in banking. Future research should focus on hybrid ML-traditional approaches and explainable AI to enhance transparency and compliance. This study underscores the potential of ML to transform banking operations, contributing to a more efficient, customer-centric banking environment