Worldwide financial markets reactions to the Covid-19 epidemic situation: A hybrid FIEGARCH-Deep learning approach

Saker Sabkha () and Sabrine Mallek ()
Additional contact information
Saker Sabkha: LEGO - Laboratoire d'Economie et de Gestion de l'Ouest - UBS - Université de Bretagne Sud - UBO EPE - Université de Brest - IMT - Institut Mines-Télécom [Paris] - IBSHS - Institut Brestois des Sciences de l'Homme et de la Société - UBO EPE - Université de Brest - UBL - Université Bretagne Loire - IMT Atlantique - IMT Atlantique - IMT - Institut Mines-Télécom [Paris]
Sabrine Mallek: ICN Business School, CEREFIGE - Centre Européen de Recherche en Economie Financière et Gestion des Entreprises - UL - Université de Lorraine

Working Papers from HAL

Abstract: The world's financial centers have been subject to several uncertainties regarding the international extension of the market shakeout in China at the end of 2019, the epicenter of the Coronavirus (Covid-19). Due to the lack of visibility that investors are dealing with in figuring out how long-lasting the uncontained epidemic will be, financial markets around the world are being worried about the impact of this health crisis. This paper aims to forecast the potential evolution of global equity markets, using data from January 2000 to April 2020 covering different pandemic periods. A new framework is adopted combining an econometric FIEGARCH model to a Long-Short Term Memory (LSTM) neural network and based on non-fundamental factors including: markets' reactions to prior epidemics (H1N1 and SARS), the observed number of contamination and the expected infection rate per country, the extent of the implemented economic measures and the virus seasonality. Results show that the global markets will continue to farewell as long as the epidemic fears are not contained and the visibility is not clear, with high-expected variations at no time observed during previous epidemics. Furthermore, a rebound would be recorded as the virus gets under control and cases number decreases, yet, with different horizons and intensities for each country. As the long-term horizon is the investment key, these results suggest facing a new wave of decline by remaining strongly invested in the euro zone and on the environmental component.

Keywords: Deep learning FIEGARCH Model LSTM stock market forecasting; Deep learning; FIEGARCH Model; LSTM; stock market forecasting (search for similar items in EconPapers)
Date: 2023-03-23
Note: View the original document on HAL open archive server: https://ubs.hal.science/hal-05556340v1
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ubs.hal.science/hal-05556340v1/document (application/pdf)

Related works:
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:wpaper:hal-05556340

Access Statistics for this paper

More papers in Working Papers from HAL
Bibliographic data for series maintained by CCSD ().