Forecasting major currency exchange rates using long short-term memory networks: Evidence from multi-currency time series analysis

Show simple item record
dc.contributor.authorGhorbani, Shahryar
dc.contributor.authorYildirim, Figen
dc.contributor.authorBicer, Ali Altug
dc.contributor.authorRostamzadeh, Reza
dc.contributor.authorSaparauskas, Jonas
dc.date.accessioned2026-06-03T08:55:38Z
dc.date.available2026-06-03T08:55:38Z
dc.date.issued2026
dc.description.abstract-translatedExchange-rate dynamics are non-linear and volatile, which challenges conventional forecasting approaches. This study evaluates a reproducible long short-term memory (LSTM) framework for daily EUR/USD, GBP/USD, USD/TRY, and USD/JPY over 1 January 2010 to 31 December 2021. The contribution is twofold: (i) a fully specified and deployment-oriented LSTM protocol (architecture, preprocessing, and leakage-safe validation) suitable for applied forecasting; and (ii) a time-series-appropriate evaluation that combines rolling-origin (walk-forward) testing with standard baselines (random walk and ARIMA) and diagnostic visualizations. Forecast performance is reported using root mean square error (RMSE), mean absolute error (MAE), Pearson correlation (R), Nash-Sutcliffe efficiency (NSE), and the RMSE-to-SD ratio (RSR), alongside distributional diagnostics (violin plots) and horizon-specific error profiles. The results quantify performance gains relative to baselines under leakage-safe evaluation, while highlighting practical implications for treasury and risk management. Limitations include the exclusion of exogenous drivers and longer-horizon tests, motivating extensions that incorporate macro-financial signals and interpretability modules.en
dc.format20 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.doihttps://doi.org/10.15240/tul/001/2026-2-014
dc.identifier.issn2336-5604 (Online)
dc.identifier.issn1212-3609 (Print)
dc.identifier.orcidGhorbani, Shahryar 0000-0001-6085-1788
dc.identifier.orcidYildirim, Figen 0000-0002-9247-2245
dc.identifier.orcidBicer, Ali Altug 0000-0002-5515-212X
dc.identifier.orcidRostamzadeh, Reza 0000-0002-6161-7173
dc.identifier.orcidSaparauskas, Jonas 0000-0003-3685-7754
dc.identifier.urihttp://hdl.handle.net/11025/68228
dc.language.isoenen
dc.publisherTechnická univerzita v Libercics
dc.rightsCC BY-NC 4.0en
dc.rights.accessopenAccessen
dc.subjectpredikce směnných kurzůcs
dc.subjecthluboké učenícs
dc.subjectLSTMcs
dc.subjectčasové řady měncs
dc.subjectpredikce výkonnostics
dc.subjectfinanční modelovánícs
dc.subjectvizuální diagnostikacs
dc.subject.translatedexchange rate forecastingen
dc.subject.translateddeep learningen
dc.subject.translatedLSTMen
dc.subject.translatedcurrency time seriesen
dc.subject.translatedforecasting performanceen
dc.subject.translatedfinancial modelingen
dc.subject.translatedvisual diagnosticsen
dc.titleForecasting major currency exchange rates using long short-term memory networks: Evidence from multi-currency time series analysisen
dc.typečlánekcs
dc.typearticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
local.files.count1*
local.files.size3461564*
local.has.filesyes*

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
14_E+M_2_2026_14.pdf
Size:
3.3 MB
Format:
Adobe Portable Document Format
Download
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Číslo 2 (2026)
Číslo 2 (2026)