Economic Forecasting with an Agent-Based Model

Abstract

We develop the first agent-based model (ABM) that can compete with and in the long run significantly outperform benchmark VAR and DSGE models in out-of-sample forecasting of macro variables. Our ABM for a small open economy uses micro and macro data from national sector accounts, input-output tables, government statistics, and census data. The model incorporates all economic activities as classified by the European System of Accounts as heterogeneous agents. The detailed structure of the ABM allows for a breakdown into sector level forecasts. In a recent application, we have used the detailed structure of the ABM to forecast the medium-run macroeconomic effects of lockdown measures taken in Austria to combat the COVID-19 crisis. Other potential applications of the model include stress-testing and predicting the effects of monetary or fiscal macroeconomic policies.

Keywords: agent-based models, behavioral macro, macroeconomic forecasting, micro data

JEL Classification: E70, E32, E37