The Analysis of Factors Affecting High and Persistent Inflation in Iran's Economy: an Approach Based on Machine Learning

High and volatile inflation has had numerous adverse effects on the Iranian economy. Effective inflation-targeting policies require a thorough understanding of the key drivers of inflation. This study aims to identify the most important determinants of inflation in the Iranian economy from 2008 to 2022. In this study, tree-based ensemble methods, which are a class of intelligent machine-learning techniques, have been utilized. Furthermore, Shapley Additive Explanations (SHAP) are utilized to interpret model predictions and determine feature importance. Model performance is evaluated using three error metrics: Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Squared Error (RMSE). Results indicate that Gradient Boosting (GB), Random Forest (RF), and Extreme Gradient Boosting (XGB) exhibit the lowest error rates across all three metrics. The findings reveal that broad money growth is the most significant determinant of inflation, contributing an average of 72% across all models. The exchange rate, while a contributing factor, plays a less substantial role compared to broad money, accounting for approximately 17% of the inflationary pressures.