On Some Deep Learning Algorithms and Grey Models for Forecasting FX Rates: A Comparative Study.

On Some Deep Learning Algorithms and Grey Models for Forecasting FX Rates: A Comparative Study. | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Systematic Review On Some Deep Learning Algorithms and Grey Models for Forecasting FX Rates: A Comparative Study. Noorshanaaz Khodabaccus, Aslam Aly El Faidal Saib This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6152025/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Volatility in the foreign exchange market is often associated with risk and may hence cause a stir in the sustainable development of an economy. The Mauritian economy, being open and globally integrated, is highly sensitive to fluctuations in other currencies. Consequently, volatility modelling and forecasting of the FX market is crucial for proper risk management exercises. This paper provides a comparative study on the FX rate modelling and forecasting accuracy of some conventionally used deep learning approaches against some grey models. In particular, we employ the recurrent neural networks and the long short-term memory recurrent networks using high-frequency historical data against the optimised Fourier grey Markov model (FOGM) using a significantly smaller dataset. We observe that the FOGM model with a smaller dataset outperforms the deep learning approaches considered. Volatility forecasting Volatility modelling Foreign exchange data Deep learning Grey model Optimised Fourier grey Markov model Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6152025","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Systematic Review","associatedPublications":[],"authors":[{"id":426126916,"identity":"991822b6-03bb-4a02-a0d5-4e4b16a04939","order_by":0,"name":"Noorshanaaz Khodabaccus","email":"","orcid":"","institution":"University of Technology, Mauritius","correspondingAuthor":false,"prefix":"","firstName":"Noorshanaaz","middleName":"","lastName":"Khodabaccus","suffix":""},{"id":426126917,"identity":"6e13f621-daf7-41d1-a212-7c73449cb76e","order_by":1,"name":"Aslam Aly El Faidal Saib","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqElEQVRIiWNgGAWjYJCCwwwVpGs5wyBBmhZmxjZStPD3H354uHDe4TrdBuaHHxhzDhPWInEjzeDwzG2HJcwOsBlLMG4jQgvDDQaDw7xgLQxmDERpkT9//MNh3jkgLezfiNNicCAHaEsDSAsPkbYY3sgpODzjWLrktsM8xRKJ29IJa5E7f3zz54Iaa36z4+0bP3zcZk1YCwIwA3ECKRpGwSgYBaNgFOAGAHBxOp4Kwt05AAAAAElFTkSuQmCC","orcid":"","institution":"University of Technology, Mauritius","correspondingAuthor":true,"prefix":"","firstName":"Aslam","middleName":"Aly El Faidal","lastName":"Saib","suffix":""}],"badges":[],"createdAt":"2025-03-04 07:53:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6152025/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6152025/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":78212031,"identity":"851e7a44-ce8d-4de7-9793-3fa608de3400","added_by":"auto","created_at":"2025-03-11 03:48:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1970755,"visible":true,"origin":"","legend":"","description":"","filename":"SwissJournalofEconomicsandStatistics.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6152025/v1_covered_0d4fd5e8-34d2-4a5a-ad30-69d65445f0e8.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"On Some Deep Learning Algorithms and Grey Models for Forecasting FX Rates: A Comparative Study.","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Volatility forecasting, Volatility modelling, Foreign exchange data, Deep learning, Grey model, Optimised Fourier grey Markov model","lastPublishedDoi":"10.21203/rs.3.rs-6152025/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6152025/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Volatility in the foreign exchange market is often associated with risk and may hence cause a stir in the sustainable development of an economy. The Mauritian economy, being open and globally integrated, is highly sensitive to fluctuations in other currencies. Consequently, volatility modelling and forecasting of the FX market is crucial for proper risk management exercises. This paper provides a comparative study on the FX rate modelling and forecasting accuracy of some conventionally used deep learning approaches against some grey models. In particular, we employ the recurrent neural networks and the long short-term memory recurrent networks using high-frequency historical data against the optimised Fourier grey Markov model (FOGM) using a significantly smaller dataset. We observe that the FOGM model with a smaller dataset outperforms the deep learning approaches considered. ","manuscriptTitle":"On Some Deep Learning Algorithms and Grey Models for Forecasting FX Rates: A Comparative Study.","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-11 03:40:01","doi":"10.21203/rs.3.rs-6152025/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"b85cf6a4-6c38-45d7-8a60-0adb5cd28923","owner":[],"postedDate":"March 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-03-11T03:40:01+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-11 03:40:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6152025","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6152025","identity":"rs-6152025","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}