Model building in Agricultural Economics with Machine Learning: Echoes from the past

Machine Learning tools are currently transforming empirical research in agricultural economics. However, a concern with these new tools is that they are purely data-driven. The history of economic science reveals a recurring tension between the roles of economic theory and data. The objective of this paper is to describe lessons from the apparent divergence between theory-driven and data-driven modelling approaches that can guide to the current rise of machine learning modelling in agricultural economics. We first discuss different views on using theory and data in economic building in general terms. Next, we review several key econometric papers in agricultural economics in order to show how economic theory and data are used. This is followed by an evaluation of agricultural economics publications that have employed machine learning techniques. Finally, we synthesize these findings in the discussion section and provide recommendations for the effective integration of machine learning in agricultural economics.