Macroeconomic Indicator Forecasting with Deep Neural Networks

39 Pages Posted: 3 Oct 2017

See all articles by Aaron Smalter Hall

Aaron Smalter Hall

Federal Reserve Bank of Kansas City

Thomas R. Cook

Federal Reserve Bank of Kansas City

Date Written: September 29, 2017

Abstract

Economic policymaking relies upon accurate forecasts of economic conditions. Current methods for unconditional forecasting are dominated by inherently linear models that exhibit model dependence and have high data demands. We explore deep neural networks as an opportunity to improve upon forecast accuracy with limited data and while remaining agnostic as to functional form. We focus on predicting civilian unemployment using models based on four different neural network architectures. Each of these models outperforms benchmark models at short time horizons. One model, based on an Encoder Decoder architecture outperforms benchmark models at every forecast horizon (up to four quarters).

JEL Classification: C45, C53, C14

Suggested Citation

Smalter Hall, Aaron and Cook, Thomas R., Macroeconomic Indicator Forecasting with Deep Neural Networks (September 29, 2017). Federal Reserve Bank of Kansas City Working Paper No. 17-11, Available at SSRN: https://ssrn.com/abstract=3046657 or http://dx.doi.org/10.2139/ssrn.3046657

Aaron Smalter Hall (Contact Author)

Federal Reserve Bank of Kansas City ( email )

1 Memorial Dr.
Kansas City, MO 64198
United States

Thomas R. Cook

Federal Reserve Bank of Kansas City ( email )

1 Memorial Dr.
Kansas City, MO 64198
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
1,037
Abstract Views
2,445
rank
30,203
PlumX Metrics