Adaptive Financial Time Series Classification: Leveraging Historical Samples from Signal-to-Noise Ratio Margins

Adaptive Financial Time Series Classification: Leveraging Historical Samples from Signal-to-Noise Ratio Margins | 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 Adaptive Financial Time Series Classification: Leveraging Historical Samples from Signal-to-Noise Ratio Margins Zhipeng Jiang, Hua zou, Dengyi Zhang, Qian Cai, Yu Li, Fuyong Liu, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7589950/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract In financial time series classification, concept drift adaptation is crucial to maintain model performance, as data distributions evolve over time. To handle concept drift, there are mainly two methods: detection-based, which uses historical data, and non-detection-based, which relies on more immediate, smaller volume real-time data. The former preserves historical patterns but comparatively exhibits hysteresis, while the latter is opposition. Thus, it remains a challenge to achieve continuous model updating while preserving historical patterns. To address this issue, we propose a novel non-detection-based method. This method retains valuable historical patterns and achieves continuous model updating by observing distribution variations, which simultaneously controls different hyperparameters on a data. Specifically, we develop the Adaptive Financial Time Series Classification Model (AFinSeqClass), which integrates the Complementary Margin Support Vector Machine (C-Margin SVM) and the Inverse Derivation Algorithm (InvDA) to handle sample and feature selection. For sample selection, C-Margin SVM is a dual-distribution approach that skillfully utilizes soft and hard margin theories to generate two distinct data distributions from one dataset. These two distributions generate a dynamic signal-to-noise ratio margin—complementary margin, which is the set difference between the soft margin and hard margin. We then select low-noise and information-rich samples from the complementary margin. For feature selection, InvDA reverses the forward derivation of financial features using cooperative co-evolution strategies to break down complex problems into smaller sub-problems, corresponding to homologous feature groups to gradually refine the feature set, maximizing the differences between features. Through the cooperation of these two algorithms, across a series of stocks, the AFinSeqClass model achieves a classification accuracy exceeding 60%. The implementation code of the AFinSeqClass model is available at https://github.com/MultiPaperCode/Adaptive-Financial-Time-Series-Classification.git. Concept drift Adaptive Financial time series Classification Model (AFinSeqClass) Complementary Margin Support Vector Machine (C-Margin SVM) Inverse Derivation Algorithm (InvDA) Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 15 Feb, 2026 Reviews received at journal 07 Dec, 2025 Reviews received at journal 06 Dec, 2025 Reviewers agreed at journal 02 Dec, 2025 Reviewers agreed at journal 01 Dec, 2025 Reviewers agreed at journal 29 Oct, 2025 Reviewers invited by journal 15 Oct, 2025 Editor assigned by journal 15 Sep, 2025 Submission checks completed at journal 15 Sep, 2025 First submitted to journal 11 Sep, 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-7589950","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":535408701,"identity":"ee493e1a-aaa9-4ebd-80cb-6b8b03c8dba8","order_by":0,"name":"Zhipeng Jiang","email":"","orcid":"","institution":"wuhan university","correspondingAuthor":false,"prefix":"","firstName":"Zhipeng","middleName":"","lastName":"Jiang","suffix":""},{"id":535408702,"identity":"da47f8fe-fa9b-44e0-aa71-dc674deec393","order_by":1,"name":"Hua zou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuUlEQVRIiWNgGAWjYHACNiC2YTAAMXlI0JJGupbDJGiRb+8xe8xTcz5xu0QC44O3bQzy5oS0MPacMTfmOXY7ceeMBGbDuW0MhjsbCGhhlsgxk+Zhu5274UYCmzRvG0OCwQFCHgFr+XcOpIX9N1FaeEBaeNsOgG1hJkqLBM+xMsm5fcn1G848bJacc07CcAMhLfLtzdsk3nyzMzY4nnzww5syG3mCtiABxgaQrcSrHwWjYBSMglGAGwAAnwE7CFXalnsAAAAASUVORK5CYII=","orcid":"","institution":"wuhan university","correspondingAuthor":true,"prefix":"","firstName":"Hua","middleName":"","lastName":"zou","suffix":""},{"id":535408703,"identity":"ce9672fc-39e8-4182-b2a5-e46dd22404e1","order_by":2,"name":"Dengyi Zhang","email":"","orcid":"","institution":"wuhan university","correspondingAuthor":false,"prefix":"","firstName":"Dengyi","middleName":"","lastName":"Zhang","suffix":""},{"id":535408704,"identity":"1c0f66c6-5b92-4b1c-b424-1940920478f8","order_by":3,"name":"Qian Cai","email":"","orcid":"","institution":"Wuhan Textile University","correspondingAuthor":false,"prefix":"","firstName":"Qian","middleName":"","lastName":"Cai","suffix":""},{"id":535408705,"identity":"28aa568b-3fde-4aaf-99e1-e5ce94703e72","order_by":4,"name":"Yu Li","email":"","orcid":"","institution":"Wuhan Textile University","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Li","suffix":""},{"id":535408706,"identity":"ce0c7eb8-07b2-42f7-a4c6-cc6cb7b1163a","order_by":5,"name":"Fuyong Liu","email":"","orcid":"","institution":"Xinjiang College of Science \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"Fuyong","middleName":"","lastName":"Liu","suffix":""},{"id":535408707,"identity":"73511962-b5c0-4b9d-adc3-35446794c729","order_by":6,"name":"Xueli Qin","email":"","orcid":"","institution":"Dongying Vocational College of Science \u0026 Technology","correspondingAuthor":false,"prefix":"","firstName":"Xueli","middleName":"","lastName":"Qin","suffix":""}],"badges":[],"createdAt":"2025-09-11 09:08:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7589950/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7589950/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94585105,"identity":"4de4b55a-3b0e-4066-802c-e21981137124","added_by":"auto","created_at":"2025-10-28 18:15:52","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8546,"visible":true,"origin":"","legend":"","description":"","filename":"2600cc0569824893a24660795c4b2f12.json","url":"https://assets-eu.researchsquare.com/files/rs-7589950/v1/5594d7c41e22d8bb098247fa.json"},{"id":94595328,"identity":"321d96c6-81a4-44be-93ee-6a8f8b5d49c4","added_by":"auto","created_at":"2025-10-28 18:33:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":660383,"visible":true,"origin":"","legend":"","description":"","filename":"AdaptiveFinancialTimeSeriesClassificationLeveragingHistoricalSamplesfromSignaltoNoiseRatioMarginsAPI2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7589950/v1_covered_1f785274-03e5-4647-9461-89097196b53d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Adaptive Financial Time Series Classification: Leveraging Historical Samples from Signal-to-Noise Ratio Margins","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"neural-processing-letters","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nepl","sideBox":"Learn more about [Neural Processing Letters](http://link.springer.com/journal/11063)","snPcode":"11063","submissionUrl":"https://submission.nature.com/new-submission/11063/3","title":"Neural Processing Letters","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Concept drift, Adaptive Financial time series Classification Model (AFinSeqClass), Complementary Margin Support Vector Machine (C-Margin SVM), Inverse Derivation Algorithm (InvDA)","lastPublishedDoi":"10.21203/rs.3.rs-7589950/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7589950/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn financial time series classification, concept drift adaptation is crucial to maintain model performance, as data distributions evolve over time. To handle concept drift, there are mainly two methods: detection-based, which uses historical data, and non-detection-based, which relies on more immediate, smaller volume real-time data. The former preserves historical patterns but comparatively exhibits hysteresis, while the latter is opposition. Thus, it remains a challenge to achieve continuous model updating while preserving historical patterns. To address this issue, we propose a novel non-detection-based method. This method retains valuable historical patterns and achieves continuous model updating by observing distribution variations, which simultaneously controls different hyperparameters on a data. Specifically, we develop the Adaptive Financial Time Series Classification Model (AFinSeqClass), which integrates the Complementary Margin Support Vector Machine (C-Margin SVM) and the Inverse Derivation Algorithm (InvDA) to handle sample and feature selection. For sample selection, C-Margin SVM is a dual-distribution approach that skillfully utilizes soft and hard margin theories to generate two distinct data distributions from one dataset. These two distributions generate a dynamic signal-to-noise ratio margin—complementary margin, which is the set difference between the soft margin and hard margin. We then select low-noise and information-rich samples from the complementary margin. For feature selection, InvDA reverses the forward derivation of financial features using cooperative co-evolution strategies to break down complex problems into smaller sub-problems, corresponding to homologous feature groups to gradually refine the feature set, maximizing the differences between features. Through the cooperation of these two algorithms, across a series of stocks, the AFinSeqClass model achieves a classification accuracy exceeding 60%. The implementation code of the AFinSeqClass model is available at https://github.com/MultiPaperCode/Adaptive-Financial-Time-Series-Classification.git.\u003c/p\u003e","manuscriptTitle":"Adaptive Financial Time Series Classification: Leveraging Historical Samples from Signal-to-Noise Ratio Margins","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-28 16:32:40","doi":"10.21203/rs.3.rs-7589950/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-15T06:32:19+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-07T23:58:01+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-07T03:49:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"175918154125393685981393847222076257366","date":"2025-12-02T15:33:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"86124857321463663463096858036432425312","date":"2025-12-01T15:21:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"237155295348007027818306878781336053308","date":"2025-10-29T07:20:38+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-15T09:45:52+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-15T07:06:54+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-15T07:05:08+00:00","index":"","fulltext":""},{"type":"submitted","content":"Neural Processing Letters","date":"2025-09-11T09:01:56+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"neural-processing-letters","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nepl","sideBox":"Learn more about [Neural Processing Letters](http://link.springer.com/journal/11063)","snPcode":"11063","submissionUrl":"https://submission.nature.com/new-submission/11063/3","title":"Neural Processing Letters","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"456b7aaf-7a6b-49ac-91a0-56c3ce6fc953","owner":[],"postedDate":"October 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-03-13T12:39:26+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-28 16:32:40","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7589950","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7589950","identity":"rs-7589950","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}