The growth of problematic bank debt and non-performing loans (NPLs) remains an important challenge for the stability, profitability, and lending capacity of commercial banks. Traditional approaches to credit-risk management, which primarily rely on historical financial information, collateral, credit history, and periodic borrower assessments, may be insufficient for identifying rapidly changing credit risks in a digital financial environment. Innovative financial technologies, including artificial intelligence, machine learning, big-data analytics, automated credit scoring, predictive analytics, digital early-warning systems, open banking, and automated debt-management platforms, create new opportunities for improving the prevention and management of problematic bank debt. The purpose of this study is to examine the role of innovative financial technologies in reducing problematic bank debt and to develop an integrated technology-based framework for credit-risk management. The research applies analytical, comparative, systemic, and conceptual modelling methods to examine the relationship between financial technologies, borrower-risk assessment, early-warning mechanisms, intervention, restructuring, and debt recovery. The results demonstrate that innovative technologies can improve the quality and speed of borrower assessment, facilitate continuous monitoring, identify early signs of financial deterioration, and support more targeted restructuring and recovery procedures. At the same time, technological solutions introduce risks associated with data quality, model accuracy, algorithmic bias, cybersecurity, privacy, and excessive dependence on automated decisions. The study proposes an integrated model in which digital data collection, artificial intelligence, predictive analytics, continuous monitoring, early-warning systems, and digital recovery mechanisms operate as interconnected components of credit-risk management. The study concludes that innovative financial technologies should complement rather than replace traditional banking risk-management principles and can contribute to the transition from reactive management of problematic debt toward proactive, continuous, and data-driven credit-risk management.