Comparative Analysis of Machine Learning and Autoregressive Models for Forecasting Economic Growth: A Case Study

This study presents a comparative analysis of machine learning models, specifically gradient boosting machine (GBM) and random forest (RF), against the traditional vector autoregressive (VAR) model for forecasting economic growth in Algeria.By utilizing a dataset comprising key macroeconomic indicators-Gross Domestic Product (GDP), money supply (M), and inflation (I)-we aim to evaluate the predictive accuracy and robustness of these models.Our findings indicate that the RF model outperforms both GBM and VAR in terms of accuracy and reliability, providing a valuable understanding of the economic dynamics of Algeria.These results highlight the potential of advanced machine learning techniques in improving economic forecasting and informing policy decisions in emerging economies.