A neural network ensemble approach for GDP forecasting

DOI10.1016/J.JEDC.2021.104278MaRDI QIDQ2115947zbMATH OpenOpenAlexFDO

Authors Luigi Longo, Armando Rungi, Massimo Riccaboni

Publication date 15 March 2022

Published in Journal of Economic Dynamics and Control (Search for Journal in Brave)

Full work available at URL http://eprints.imtlucca.it/4081/

zbMATH Keywords

COVID-19 crisisdynamic factor modelmachine learningmacroeconomic forecastingneural networks

Mathematics Subject Classification ID

Game theory, economics, finance, and other social and behavioral sciences (91-XX)

Recommendations

• Inflation forecasting using a neural network
• Forecasting economic growth using financial variables -- comparison of linear regression and neural network models
• Forecasting GDP in Asian countries using relevant vector machines
• Nonlinear and nonparametric modeling approaches for probabilistic forecasting of the US gross national product
• Global prediction of recessions

Cites work

• Approximately normal tests for equal predictive accuracy in nested models
• scientific article; zbMATH DE number 3078997 (Why is no real title available?)
• Tests of Equality Between Sets of Coefficients in Two Linear Regressions
• The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions
• Time series analysis by state space methods.

Cited in

(4)

• Forecasts of GDP growth and inflation under the influence of the Covid-19 pandemic: the case of Vietnam
• Macroeconomic forecasting based on LSTM-conditioned normalizing flows
• On the impact of the Covid-19 health crisis on GDP forecasting: an empirical approach
• On the information content of explainable artificial intelligence for quantitative approaches in finance

Describes a project that uses

Uses Software

• TensorFlow
• shap

This page was built for publication: A neural network ensemble approach for GDP forecasting

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2115947)