Predictive economics: Rethinking economic methodology with machine learning

TL;DR

Predictive economics argues for a distinct economic methodology that treats predictive accuracy, especially out-of-sample performance, as a legitimate objective. Grounded in instrumentalism, the explanation–prediction distinction, and Breiman’s two-cultures idea, it advocates methodological pluralism where machine-learning predictions inform policy alongside traditional theory and causal analysis. The paper surveys micro-, macro-, and related subfields, showing that predictive models can improve forecasting, targeting, and decision-making in complex or data-rich contexts, while acknowledging limits such as regime changes and opacity. It concludes that prediction should complement rather than replace theory, enabling more flexible, data-driven policy design and real-time decision support across economics.

Abstract

This article proposes predictive economics as a distinct analytical perspective within economics, grounded in machine learning and centred on predictive accuracy rather than causal identification. Drawing on the instrumentalist tradition (Friedman), the explanation-prediction divide (Shmueli), and the contrast between modelling cultures (Breiman), we formalise prediction as a valid epistemological and methodological objective. Reviewing recent applications across economic subfields, we show how predictive models contribute to empirical analysis, particularly in complex or data-rich contexts. This perspective complements existing approaches and supports a more pluralistic methodology - one that values out-of-sample performance alongside interpretability and theoretical structure.