Comparison of the accuracy of forecasts based on neural networks before and after the outbreak of the COVID-19 pandemic on the example of selected exchange rates

This article examines the impact of the COVID-19 pandemic on the accuracy of forecasts for three currency pairs before and after its outbreak based on neural networks (ELM, MLP and LSTM) in terms of three factors: the forecast horizon, hyper parameterisation and network type.

Saved in:
Bibliographic Details
Published inPrzegląd statystyczny Vol. 69; no. 4; pp. 41 - 60
Main Author Morkowski, Jakub
Format Journal Article
LanguageEnglish
Published Statistics Poland 2022
Główny Urząd Statystyczny
Subjects
Economy
currency market
COVID19 pandemic
neural network
forecasts
Online AccessGet full text

Cover

More Information
Summary:This article examines the impact of the COVID-19 pandemic on the accuracy of forecasts for three currency pairs before and after its outbreak based on neural networks (ELM, MLP and LSTM) in terms of three factors: the forecast horizon, hyper parameterisation and network type.
ISSN:0033-2372
2657-9545