Using Machine Learning to Generate, Clarify, and Improve Economic Models

TL;DR

This paper explores how machine learning can be adapted to develop economic models that not only predict outcomes more accurately but also reveal underlying mechanisms, thereby aiding policy and theory development.

Contribution

It demonstrates that with specific modifications, machine learning can be used to create economic models that improve understanding and causal inference, not just prediction.

Findings

Machine learning outperforms traditional models in economic prediction tasks.

Modified algorithms can uncover causal pathways in economic development.

Integrating economic theory with machine learning enhances model interpretability.

Abstract

Machine learning algorithms can now outperform classic economic models in predicting quantities ranging from bargaining outcomes, to choice under uncertainty, to an individual's future jobs and wages. Yet this predictive accuracy comes at a cost: most machine learning algorithms function as black boxes, offering little insight into \emph{why} outcomes occur. This article asks whether machine learning can guide the development of new economic theories. Economic models serve an important purpose beyond prediction -- they uncover the general mechanisms behind observed behaviors. A model that identifies the causal pathways of economic development is more valuable than one that merely predicts which countries will escape poverty, because it enables policymakers to encourage that development in countries where it might not have happened otherwise. Similarly, a model that predicts imperfectly across many domains can be more valuable than one that is highly accurate in a specific domain, since the former allows insights and data obtained from one setting to inform decisions and policy in another. Applying machine learning algorithms off-the-shelf is unlikely to yield such models. But recent work shows that, when reconceived with the aims of an economic modeler in mind, machine learning methods can improve both prediction and understanding. These approaches range from adversarially training algorithms to expose the limits of existing models, to imposing economic theory as a constraint on algorithmic search. Advances in large language models complement these strategies and open new research directions.