Forecasting Inflation in Latin American Countries Using a SARIMA-LSTM Combination

Forecasting Inflation in Latin American Countries Using a SARIMA-LSTM Combination | 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 Research Article Forecasting Inflation in Latin American Countries Using a SARIMA-LSTM Combination Rodrigo Peirano, Werner Kristjanpoller, Marcel Minutolo This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-607554/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 10 Jul, 2021 Read the published version in Soft Computing → Version 1 posted 5 You are reading this latest preprint version Abstract Inflation forecasting has been and continues to be an important issue for the world's economies. Governments, through their central banks, watch closely inflation indicators to make national decisions and policies. Controlling growth and contraction requires governments to keep a close eye on the rate of inflation. When planning strategic national investments, governments attempt to forecast inflation over longer periods of time. Getting the inflation forecast wrong, can result in significant economic hardships. However, even given its significance, there is limited new research that applies updated methodologies to forecast it, and even fewer studies in emerging economies where inflation may be drastically higher. This study proposes to forecast the inflation rate in emerging economies based on the commonly used Seasonal Autoregressive Integrated Moving Average (SARIMA) approach combined with Long Short Term Memory (LSTM). The results indicate that the proposed model based on the combination of SARIMA and LSTM, have a higher accuracy in inflation forecasts as measured by the Mean Square Error (MSE) of the proposed models over the SARIMA model and LSTM alone. The loss function used is Mean Squared Error (MSE), and the Model Confidence Set (MCS) is used to test the superiority of the models in the economies of Mexico, Colombia and Peru. Theoretical Computer Science Inflation Forecasting Econometrics Models Artificial Intelligence Models Hybrid model Time series forecasting. Figures Figure 1 Figure 2 Figure 3 Full Text Supplementary Files Highlights.docx Cite Share Download PDF Status: Published Journal Publication published 10 Jul, 2021 Read the published version in Soft Computing → Version 1 posted Editorial decision: Accept 28 Jun, 2021 Reviews received at journal 14 Jun, 2021 Reviewers invited by journal 09 Jun, 2021 Editor assigned by journal 09 Jun, 2021 First submitted to journal 08 Jun, 2021 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-607554","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":32429018,"identity":"0ec171fc-64e8-4070-88e9-f120306b64af","order_by":0,"name":"Rodrigo Peirano","email":"","orcid":"","institution":"Universidad Tecnica Federico Santa Maria","correspondingAuthor":false,"prefix":"","firstName":"Rodrigo","middleName":"","lastName":"Peirano","suffix":""},{"id":32429019,"identity":"79ab3035-37b3-4425-8138-c2d51aea4b53","order_by":1,"name":"Werner Kristjanpoller","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0002-5878-072X","institution":"Universidad Tecnica Federico Santa Maria","correspondingAuthor":true,"prefix":"","firstName":"Werner","middleName":"","lastName":"Kristjanpoller","suffix":""},{"id":32429020,"identity":"ea83e333-9705-4ed7-b5d3-7adf694ebba1","order_by":2,"name":"Marcel Minutolo","email":"","orcid":"","institution":"Robert Morris University","correspondingAuthor":false,"prefix":"","firstName":"Marcel","middleName":"","lastName":"Minutolo","suffix":""}],"badges":[],"createdAt":"2021-06-10 01:46:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-607554/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-607554/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00500-021-06016-5","type":"published","date":"2021-07-10T15:00:31+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":10350410,"identity":"7c2793d2-52fa-4dc0-bc31-41fe54d50307","added_by":"auto","created_at":"2021-06-14 17:58:32","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":65929,"visible":true,"origin":"","legend":"Basic representation of the LSTM","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-607554/v1/11079728205c9b2650757a84.png"},{"id":10350922,"identity":"475d0aba-8e0d-4b60-a782-bd76cd2c0ecc","added_by":"auto","created_at":"2021-06-14 18:01:32","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":48780,"visible":true,"origin":"","legend":"Graphic representation of the proposed methodology","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-607554/v1/773179b7d493f6de00199fbc.png"},{"id":10350924,"identity":"5f0299f8-d1f7-4718-b5c1-55f7c23343b2","added_by":"auto","created_at":"2021-06-14 18:01:32","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":103615,"visible":true,"origin":"","legend":"Inflation Series","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-607554/v1/0eb6138db78336ab0ff93e47.png"},{"id":13698495,"identity":"3edeb41d-38b8-40fc-ae1c-faa19cad2e2c","added_by":"auto","created_at":"2021-09-17 13:14:52","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":369899,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-607554/v1/0cb76762-cd25-4fbe-823e-023501be8394.pdf"},{"id":10350414,"identity":"e9f4da95-82e3-436f-9e52-c659b665f6fc","added_by":"auto","created_at":"2021-06-14 17:58:32","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":12932,"visible":true,"origin":"","legend":"","description":"","filename":"Highlights.docx","url":"https://assets-eu.researchsquare.com/files/rs-607554/v1/558c12240a0ed6757bdada44.docx"}],"financialInterests":"","formattedTitle":"\u003cp\u003eForecasting Inflation in Latin American Countries Using a SARIMA-LSTM Combination\u003c/p\u003e","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-607554/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Inflation Forecasting, Econometrics Models, Artificial Intelligence Models, Hybrid model, Time series forecasting.","lastPublishedDoi":"10.21203/rs.3.rs-607554/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-607554/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Inflation forecasting has been and continues to be an important issue for the world's economies. Governments, through their central banks, watch closely inflation indicators to make national decisions and policies. Controlling growth and contraction requires governments to keep a close eye on the rate of inflation. When planning strategic national investments, governments attempt to forecast inflation over longer periods of time. Getting the inflation forecast wrong, can result in significant economic hardships. However, even given its significance, there is limited new research that applies updated methodologies to forecast it, and even fewer studies in emerging economies where inflation may be drastically higher. This study proposes to forecast the inflation rate in emerging economies based on the commonly used Seasonal Autoregressive Integrated Moving Average (SARIMA) approach combined with Long Short Term Memory (LSTM). The results indicate that the proposed model based on the combination of SARIMA and LSTM, have a higher accuracy in inflation forecasts as measured by the Mean Square Error (MSE) of the proposed models over the SARIMA model and LSTM alone. The loss function used is Mean Squared Error (MSE), and the Model Confidence Set (MCS) is used to test the superiority of the models in the economies of Mexico, Colombia and Peru.","manuscriptTitle":"Forecasting Inflation in Latin American Countries Using a SARIMA-LSTM Combination","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2021-06-14 17:58:30","doi":"10.21203/rs.3.rs-607554/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Accept","date":"2021-06-28T12:37:39+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2021-06-15T00:00:00+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2021-06-09T15:24:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2021-06-09T04:23:00+00:00","index":"","fulltext":""},{"type":"submitted","content":"Soft Computing","date":"2021-06-08T18:46:03+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"868a00b6-674c-4fb8-9b89-ec724e9613ca","owner":[],"postedDate":"June 14th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":5009286,"name":"Theoretical Computer Science"}],"tags":[],"updatedAt":"2021-08-10T15:04:33+00:00","versionOfRecord":{"articleIdentity":"rs-607554","link":"https://doi.org/10.1007/s00500-021-06016-5","journal":{"identity":"soft-computing","isVorOnly":false,"title":"Soft Computing"},"publishedOn":"2021-07-10 15:00:31","publishedOnDateReadable":"July 10th, 2021"},"versionCreatedAt":"2021-06-14 17:58:30","video":"","vorDoi":"10.1007/s00500-021-06016-5","vorDoiUrl":"https://doi.org/10.1007/s00500-021-06016-5","workflowStages":[]},"version":"v1","identity":"rs-607554","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-607554","identity":"rs-607554","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}