AN INTELLIGENT HYBRID FRAMEWORK FOR SYSTEMIC CYBER RISK MANAGEMENT IN CRITICAL FINANCIAL INFRASTRUCTURE

Abstract

This work looks at how cyber dangers grow harder to manage within vital financial systems, because old methods struggle when faced with tight connections across networks and fast-changing attack patterns. Although past studies point out that artificial intelligence, machine learning, or deep learning might help spot and anticipate digital threats, such tools often operate in isolation - failing to connect with models that assess broader system-wide risks or support strategic choices. Despite existing gaps, this research introduces a smart combined structure linking systemic risk assessment, statistical economics methods, together with artificial intelligence tools inside one cybersecurity oversight setup. Built around four connected components, it begins with a level tracking chain reaction across monetary systems. Following that comes a section using economic data techniques to measure how risks and controls influence outcomes. Then appears a part powered by machine learning aimed at spotting dangers early while forecasting future patterns. Finally, there exists a stage focused on improving choices about responses and where to assign support effectively. Beginning with structure, this method ties network patterns to live data signals for spotting cyber dangers early. Rather than just flagging issues, it guides choices in security planning through forward-looking insights. Fresh in its design, the research brings together separate analytical strands into one working system. Banks and similar organizations can apply these findings to strengthen their defenses where digital attacks are concerned.)