An Economy of Neural Networks: Learning from Heterogeneous Experiences

TL;DR

This paper models economic agents as neural networks learning from personal experiences, revealing how irrational behaviors and learning traps can explain wealth distribution puzzles and impact mobility.

Contribution

It introduces a neural network-based approach to model heterogeneous agents in macro-financial settings, highlighting the effects of learning dynamics on economic outcomes.

Findings

Neural agents exhibit higher average MPC.

Learning traps lead to excessive or no savings.

Learning negatively impacts intergenerational mobility.

Abstract

This paper proposes a new way to model behavioral agents in dynamic macro-financial environments. Agents are described as neural networks and learn policies from idiosyncratic past experiences. I investigate the feedback between irrationality and past outcomes in an economy with heterogeneous shocks similar to Aiyagari (1994). In the model, the rational expectations assumption is seriously violated because learning of a decision rule for savings is unstable. Agents who fall into learning traps save either excessively or save nothing, which provides a candidate explanation for several empirical puzzles about wealth distribution. Neural network agents have a higher average MPC and exhibit excess sensitivity of consumption. Learning can negatively affect intergenerational mobility.