Efficient data selection for time series forecasting using a lightweight linear proxy framework

Efficient data selection for time series forecasting using a lightweight linear proxy framework | 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 Article Efficient data selection for time series forecasting using a lightweight linear proxy framework xiang Ao, Mengru Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8425294/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 09 Apr, 2026 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Time series forecasting is pivotal in domains such as finance, transportation, and meteorology. In practical engineering applications, model performance hinges on the quality and quantity of data. However, the dual challenges of noise and redundancy in large-scale datasets, coupled with data scarcity in specific scenarios, remain significant hurdles. To address these issues, this paper proposes a unified data selection framework based on Linear Proxy and Mirrored Influence. This approach aims to rapidly evaluate sample value through lightweight forward passes, thereby circumventing expensive gradient calculations. The proposed method achieves two core functions within a unified architecture. Firstly, for standard training scenarios, we design an in-domain pre-selection mechanism guided by a validation set. This mechanism effectively identifies and eliminates detrimental samples prior to training, significantly enhancing both the training efficiency and prediction accuracy of the subsequent main model. Secondly, for few-shot scenarios, we propose a cross-domain data retrieval strategy. Leveraging limited target domain data as guidance, this strategy adaptively selects beneficial samples with consistent distributions from a large-scale source domain pool, effectively mitigating the data scarcity problem. Extensive experiments demonstrate that our method effectively resolves the challenges of training set denoising and cross-domain data augmentation while significantly reducing computational costs. Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 09 Apr, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 11 Feb, 2026 Reviews received at journal 09 Feb, 2026 Reviews received at journal 16 Jan, 2026 Reviewers agreed at journal 09 Jan, 2026 Reviewers agreed at journal 08 Jan, 2026 Reviewers invited by journal 08 Jan, 2026 Editor invited by journal 31 Dec, 2025 Editor assigned by journal 25 Dec, 2025 Submission checks completed at journal 25 Dec, 2025 First submitted to journal 22 Dec, 2025 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-8425294","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":571835070,"identity":"0460b9ab-d709-4f8f-ade3-c450ca0dbe06","order_by":0,"name":"xiang Ao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/0lEQVRIiWNgGAWjYLCCBBjjQQWQYGdgYGwgWkvCGQYGHmZitMBBYhsRWvjbG9gkHtTcsWtgP2P4IHGeTeJ+ZuaDD2cw2Mnp4tAnceYAs0HCsWfJDTxpyQaJ29ISe5jZkg03MCQbmx3AYc2NBMYHCWyHkxkYko9JJG47DNTCYyb5gOFA4jYcWuRvJDAcSPgH1ML/sP1H4hwitBiAbElsO2zHIJF8jCGxAaplAx4thmcONhsk9h1OYJN4liyRcCzNuOcw0C8zDHD7Re548zHJH98O2/Pz5xh++FBjI9ve3nzwYU+FnRxO70PjABQjKA7GpRwB7AkrGQWjYBSMghELAC+RXU/2/eXjAAAAAElFTkSuQmCC","orcid":"","institution":"Beijing Jiaotong University","correspondingAuthor":true,"prefix":"","firstName":"xiang","middleName":"","lastName":"Ao","suffix":""},{"id":571835072,"identity":"e240272e-ef47-4faa-beae-f6a6363448d9","order_by":1,"name":"Mengru Chen","email":"","orcid":"","institution":"Beijing Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Mengru","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2025-12-22 14:04:58","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8425294/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8425294/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-026-43645-y","type":"published","date":"2026-04-09T15:57:39+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":100102235,"identity":"1661cf28-ba3d-45bc-95e5-c6d02c8d47fb","added_by":"auto","created_at":"2026-01-13 03:38:45","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4649,"visible":true,"origin":"","legend":"","description":"","filename":"f39a0ed54f8e4d2085531377b8664d3d.json","url":"https://assets-eu.researchsquare.com/files/rs-8425294/v1/6c930f652dff9d7da9483ffa.json"},{"id":106808799,"identity":"90a4be6a-da52-458c-9ffe-42f9f794898d","added_by":"auto","created_at":"2026-04-13 16:01:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":439781,"visible":true,"origin":"","legend":"","description":"","filename":"LPMirrorSR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8425294/v1_covered_a443da5c-2fde-44c1-9670-1aad74a5af8a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Efficient data selection for time series forecasting using a lightweight linear proxy framework","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8425294/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8425294/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Time series forecasting is pivotal in domains such as finance, transportation, and meteorology. In practical engineering applications, model performance hinges on the quality and quantity of data. However, the dual challenges of noise and redundancy in large-scale datasets, coupled with data scarcity in specific scenarios, remain significant hurdles. To address these issues, this paper proposes a unified data selection framework based on Linear Proxy and Mirrored Influence. This approach aims to rapidly evaluate sample value through lightweight forward passes, thereby circumventing expensive gradient calculations. The proposed method achieves two core functions within a unified architecture. Firstly, for standard training scenarios, we design an in-domain pre-selection mechanism guided by a validation set. This mechanism effectively identifies and eliminates detrimental samples prior to training, significantly enhancing both the training efficiency and prediction accuracy of the subsequent main model. Secondly, for few-shot scenarios, we propose a cross-domain data retrieval strategy. Leveraging limited target domain data as guidance, this strategy adaptively selects beneficial samples with consistent distributions from a large-scale source domain pool, effectively mitigating the data scarcity problem. Extensive experiments demonstrate that our method effectively resolves the challenges of training set denoising and cross-domain data augmentation while significantly reducing computational costs.","manuscriptTitle":"Efficient data selection for time series forecasting using a lightweight linear proxy framework","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-13 03:38:12","doi":"10.21203/rs.3.rs-8425294/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-11T08:04:04+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-09T09:08:44+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-16T12:48:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"249262848008606499872200849390604564525","date":"2026-01-09T05:31:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"74417706076330790194760248664762333782","date":"2026-01-09T04:48:38+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-09T02:42:58+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-12-31T09:58:22+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-26T03:21:37+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-26T03:20:33+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-12-22T12:53:10+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"99408224-010b-4252-aee8-3f1cf8e91349","owner":[],"postedDate":"January 13th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":60854363,"name":"Physical sciences/Engineering"},{"id":60854364,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-13T16:00:17+00:00","versionOfRecord":{"articleIdentity":"rs-8425294","link":"https://doi.org/10.1038/s41598-026-43645-y","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-04-09 15:57:39","publishedOnDateReadable":"April 9th, 2026"},"versionCreatedAt":"2026-01-13 03:38:12","video":"","vorDoi":"10.1038/s41598-026-43645-y","vorDoiUrl":"https://doi.org/10.1038/s41598-026-43645-y","workflowStages":[]},"version":"v1","identity":"rs-8425294","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8425294","identity":"rs-8425294","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}