Machine learning in agricultural and applied economics

Abstract

This review presents machine learning (ML) approaches from an applied economist’s perspective. We first introduce the key ML methods drawing connections to econometric practice. We then identify current limitations of the econometric and simulation model toolbox in applied economics and explore potential solutions afforded by ML. We dive into cases such as inflexible functional forms, unstructured data sources and large numbers of explanatory variables in both prediction and causal analysis, and highlight the challenges of complex simulation models. Finally, we argue that economists have a vital role in addressing the shortcomings of ML when used for quantitative economic analysis.

Estimation of Soil Cohesion Using Machine Learning Method: A Random Forest Approach

“…More recently, machine learning (ML) or artificial intelligence (AI) based on computer science has gradually become popular and applied in many different fields [16][17][18]. e wide applications of ML have been applied in areas of the construction industry, such as determining the critical force of steel [19].…”

China's Missing Pigs: Correcting China's Hog Inventory Data Using a Machine Learning Approach

“…Arthur Samuel (1959) first coined the term machine learning, which refers to computer algorithms that improve automatically through experience. Economists use ML for prediction in estimating productivity (Chalfin et al 2016 Woodard (2016) and Storm, Baylis, and Heckelei (2019). the statistical learning theory developed by Vapnik and Chervonenkis (1974;see Vapnik 2013 for a textbook treatment in English), which spells out the discrepancy between training errors and prediction errors.…”

“…Due to data availability, structural change, and the biological cycles of agricultural production, forecasting tasks in agricultural economics often involves time series data with limited sample size. The advance of machine learning (ML), broadly defined as computer algorithms that automatically improve performance, offers appealing alternatives to traditional forecasting tools (Storm, Baylis, and Heckelei 2019). Support vector regression (SVR) is especially promising for small sample time‐series forecasting common in agricultural economics.…”

International agricultural trade forecasting using machine learning

“…Originally due to Anderson (1979) and applied to data in Anderson and van Wincoop (2003), the gravity model provides the causal association needed to implement ML algorithms in the predictive domain (Santos Silva and Tenreyro, 2006;Yotov et al, 2016;Athey and Imbens, 2019). In doing so, this study offers an alternative to time-series projections and expert judgment analyses by relying on neural networks and boosting approaches that allow for alternative and robust specifications of complex economic relationships (Baxter and Hersh, 2017;Storm et al, 2019). ML models can also provide accurate predictions, a priority of many economists in recent months given the trade disruptions among the major economies of the world.…”