Deep learning models for forecasting and analyzing the implications of COVID-19 spread on some commodities markets volatilities

Jules Sadefo-Kamdem, Rose Bandolo Essomba and James Njong Berinyuy
Additional contact information
Jules Sadefo-Kamdem: MRE - Montpellier Recherche en Economie - UM - Université de Montpellier
Rose Bandolo Essomba: African Institute for Mathematical Sciences (AIMS-Cameroon)
James Njong Berinyuy: African Institute for Mathematical Sciences (AIMS-Cameroon)
Authors registered in the RePEc Author Service: Jules SADEFO KAMDEM

Post-Print from HAL

Abstract: Over the past few years, the application of deep learning models to finance has received much attention from investors and researchers. Our work continues this trend, presenting an application of a Deep learning model, long-term short-term memory (LSTM), for the forecasting of commodity prices. The obtained results predict with great accuracy the prices of commodities including crude oil price (98.2 price(88.2 on the variability of the commodity prices. This involved checking at the correlation and the causality with the Ganger Causality method. Our results reveal that the coronavirus impacts the recent variability of commodity prices through the number of confirmed cases and the total number of deaths. We then investigate a hybrid ARIMA-Wavelet model to forecast the coronavirus spread. This analyses is interesting as a consequence of the strong causal relationship between the coronavirus(number of confirmed cases) and the commodity prices, the prediction of the evolution of COVID-19 can be useful to anticipate the future direction of the commodity prices.

Keywords: Forecasting; Covid-19 spread; Deep learning; LSTM; ARIMA-Wavelet; Commodity; market volatility; Pandemics risks (search for similar items in EconPapers)
Date: 2020-11
Note: View the original document on HAL open archive server: https://hal.umontpellier.fr/hal-02921304
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (20)

Published in Chaos, Solitons & Fractals, 2020, 140, pp.110215. ⟨10.1016/j.chaos.2020.110215⟩

Downloads: (external link)
https://hal.umontpellier.fr/hal-02921304/document (application/pdf)

Related works:
Journal Article: Deep learning models for forecasting and analyzing the implications of COVID-19 spread on some commodities markets volatilities (2020)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-02921304

DOI: 10.1016/j.chaos.2020.110215

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().