Evaluation of International Monetary Policy Coordination: Evidence from Machine Learning Algorithms

Being a critical for integrating of the global financial system, international monetary policy coordination deserves attention to offer timely and vital information about the ongoing interaction between monetary policy practices and its future. This paper reveals the integration of economies in international monetary policy coordination and the underlying adjustment dynamics of this process in advanced and emerging economies. We perform convolutional signal analysis, K-means clustering, and classification algorithms to extract similar features or patterns of monetary policy actions implemented in different economies. The empirical results show that emerging economies are more vulnerable to internal and external shocks than advanced economies due to their financial vulnerabilities. Advanced and emerging economies respond similarly but differently within their clusters. Global monetary conditions are the key driver of monetary policy decisions; however, output growth, international reserves, policy rate, credit default swap, and consumer price index are the other important country-specific determinants. This study enhances our comprehension of the intricate dynamics within monetary policy interactions among advanced and emerging economies, shedding light on the nuanced dynamics of leader–follower relationships. Additionally, this paper not only extends the literature on international monetary policy coordination by using a state-of-the-art dataset and analysis, but also provides a solid foundation for future research on this topic.