Monetary policy shocks, financial deepening and economic growth in Tanzania: a machine learning approach

This study examines the impact of monetary policy shocks and financial deepening on economic growth in Tanzania using a machine learning approach, focusing on XGBoost regression. By leveraging quarterly macroeconomic data, the study explores how changes in interest rates, money supply and inflation influence private sector credit expansion (financial deepening) and, in turn, GDP growth. The XGBoost model effectively captures complex, nonlinear relationships, providing deeper insights into the interactions between monetary policy decisions and economic performance. The results indicate that monetary policy variables dominate GDP growth, while financial deepening contributes positively but with lower influence in the short term. A Difference-in-Differences (DiD) analysis also reveals that monetary policy shocks negatively impact GDP growth. At the same time, the SARIMAX model suggests that GDP follows a predictable yet mean-reverting pattern, with weak persistence of external shocks. These findings underscore the critical role of monetary policy in macroeconomic management and highlight the need for data-driven policy interventions to enhance financial deepening and economic stability.