AI and Machine Learning in Macroeconomic Forecasting: A Systematic Review of Models, Trends, and Challenges

The combination of hybrid econometric models, machine learning (ML), and artificial intelligence (AI) has revolutionized the field of macroeconomic forecasting. This paper comprehensively reviews macroeconomic forecasting methodologies, emphasizing the shift from traditional statistical techniques to AI-driven approaches. It systematically examines recent developments in deep learning architectures, natural language processing (NLP), ensemble learning, and hybrid AI models to forecast essential economic indicators such as GDP growth, inflation, financial stability, monetary policy trends, credit risk, exchange rate movements, and sovereign risk. The study evaluates the advantages and limitations of ML-based forecasting methods, identifies emerging trends in big data analytics, and addresses practical challenges associated with AI adoption, including in-terpretability, computational efficiency, and data reliability. The results give a roadmap for incorporating AI -enhanced forecasting methodologies into macroeconomic decision-making and offer practical insights for central banks, governments, financial in-stitutions, and researchers.