Economic Forecasting with an Agent-Based Model

63 Pages Posted: 18 Nov 2019

See all articles by Sebastian Poledna

Sebastian Poledna

International Institute for Applied Systems Analysis (IIASA)

Michael Gregor Miess

Vienna University of Economics and Business

Cars H. Hommes

University of Amsterdam - Amsterdam School of Economics (ASE); CeNDEF; Tinbergen Institute

Date Written: November 11, 2019

Abstract

We develop the first agent-based model (ABM) that can compete with 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 and sector accounts, input-output tables, government statistics, census and business demography 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. Potential applications of the model include stress-testing and predicting the effects of changes in monetary, fiscal, or other macroeconomic policies.

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

JEL Classification: E70, E32, E37

Suggested Citation

Poledna, Sebastian and Miess, Michael Gregor and Hommes, Cars H., Economic Forecasting with an Agent-Based Model (November 11, 2019). Available at SSRN: https://ssrn.com/abstract=3484768 or http://dx.doi.org/10.2139/ssrn.3484768

Sebastian Poledna

International Institute for Applied Systems Analysis (IIASA) ( email )

Schlossplatz 1
Laxenburg, A-2361
Austria

Michael Gregor Miess

Vienna University of Economics and Business ( email )

Welthandelsplatz 1
Vienna, Wien 1020
Austria

Cars H. Hommes (Contact Author)

University of Amsterdam - Amsterdam School of Economics (ASE) ( email )

Center for Nonlinear Dynamics in Economics and Finance
1018 WB Amsterdam
Netherlands
+31 20 525 4246 (Phone)
+31 20 525 4349 (Fax)

CeNDEF ( email )

Roetersstraat 11
Amsterdam, NL-1018WB
Netherlands

HOME PAGE: http://www1.fee.uva.nl/cendef/

Tinbergen Institute ( email )

Burg. Oudlaan 50
Rotterdam, 3062 PA
Netherlands

Register to save articles to
your library

Register

Paper statistics

Downloads
152
Abstract Views
676
rank
197,823
PlumX Metrics