Early Warning System for Currency Crises using Long Short-Term Memory and Gated Recurrent Unit Neural Networks

Sylvain Barthélémy, Fabien Rondeau and Virginie Gautier
Additional contact information
Sylvain Barthélémy: TAC Economics, Saint-Hilaire-des-Landes, France
Virginie Gautier: TAC Economics and University of Rennes, France.

Economics Working Paper Archive (University of Rennes & University of Caen) from Center for Research in Economics and Management (CREM), University of Rennes, University of Caen and CNRS

Abstract: Currency crises, recurrent events in economic history for developing, emerging and developed countries, generate disastrous economic consequences. This paper proposes an early warning system for currency crises using sophisticated recurrent neural networks like Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). These models were initially used in language processing where they performed well. Such models are increasingly used in forecasting Financial asset prices, including exchange rates, but they have not yet been applied to the prediction of currency crises. As for all recurrent neural networks, they allow to take into account non-linear interactions between variables and the influence of past data in a dynamic form. For a set of 68 countries including developed, emerging and developing economies over the period 1995-2020, LSTM and GRU outperformed our benchmark models. LSTM and GRU correctly sent continous signals within a two-year warning window to alert 91% of the crises. For LSTM, false signals represent only 14% of the emitted signals compared to 23% for the logistic regression, making them efficient early warning systems for policymakers.

Keywords: currency crises; early warning system; neural network; long short-term memory; gated recurrent unit (search for similar items in EconPapers)
JEL-codes: F14 F31 F47 (search for similar items in EconPapers)
Date: 2023-04
New Economics Papers: this item is included in nep-big, nep-cmp, nep-fdg, nep-his and nep-mon
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://ged.univ-rennes1.fr/nuxeo/site/esupversion ... 88-be81-52a4c1ec30c1 (application/pdf)

Related works:
Journal Article: Early warning system for currency crises using long short‐term memory and gated recurrent unit neural networks (2024)
Working Paper: Early warning system for currency crises using long short‐term memory and gated recurrent unit neural networks (2024)
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:tut:cremwp:2023-05

Ordering information: This working paper can be ordered from
CREM (UMR CNRS 6211) - Faculty of Economics, 7 place Hoche, 35065 Rennes Cedex - France

Access Statistics for this paper

More papers in Economics Working Paper Archive (University of Rennes & University of Caen) from Center for Research in Economics and Management (CREM), University of Rennes, University of Caen and CNRS CREM (UMR CNRS 6211) – Faculty of Economics, 7 place Hoche, 35065 RENNES Cedex. Contact information at EDIRC.
Bibliographic data for series maintained by GERMAIN Lucie ().