A Generalized Method of Moderation for Consumption under Uncertainty

Download

• Paper Website

Abstract

Deep learning methods for solving dynamic economic models offer computational advantages over traditional grid-based approaches but produce “black box” solutions that lack transparency. This paper develops Economics Informed Neural Networks (EINNs) through a generalized method of moderation that embeds simple behavioral bounds derived from economic theory directly into neural network architectures.

Citation

Lujan, Alan. 2025. “A Generalized Method of Moderation for Consumption under Uncertainty.” Job Market Paper. https://alanlujan91.github.io/einn/.

Funding

Supported by Alfred P. Sloan Foundation through Grant No. 2025-79177.