This study reviews existing research on how climate-related risks impact banks’ operational risk. While global interest in this issue is increasing, related literature remains limited. Various analytical methods, including econometrics, statistics, and machine learning, have been used to examine this relationship. To address research gaps, this paper proposes a three-step approach integrating variable selection, statistical analysis and agent-based modeling (ABM). Statistical and machine learning techniques identify risk patterns and predict disruptions. These insights are then incorporated into an ABM framework to simulate interactions among banks, regulators, employees, and infrastructure under different climate scenarios. This methodology also addresses data scarcity by leveraging real-world climate and financial datasets, enhancing predictive accuracy. This approach enhances predictive accuracy and strengthens risk mitigation strategies. The proposed framework offers valuable tools for financial institutions and policymakers to manage operational risks in an increasingly uncertain climate landscape.