Vector Semantics at Scale: An AI Pipeline for Financial Text Similarity

Vector Semantics at Scale: An AI Pipeline for Financial Text Similarity | 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Article Vector Semantics at Scale: An AI Pipeline for Financial Text Similarity Vipul Razdan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8696862/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 This paper presents an end-to-end AI system that transforms unstructured corporate filings into vector representations and computes interpretable similarity signals using tf-idf and cosine metrics within a distributed pipeline. The approach unifies robust preprocessing (token normalization, stemming/lemmatization) with scalable retrieval, parsing, and clustering, enabling comparative analysis of accounting policy narratives across firms and time. Extensive empirical evaluation quantifies how these similarity features relate to firm-level attributes and investor behavior, illustrating how classic NLP can yield actionable structure from financial disclosures at web scale. The design and experiments offer a reproducible blueprint for AI-driven text analytics in regulated domains, coupling information retrieval methods with cloud compute for high-throughput document understanding. Cosine similarity TF-IDF financial text mining distributed computing EDGAR document clustering natural language processing accounting comparability Full Text Additional Declarations The authors declare no competing interests. Associated Publications 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-8696862","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[{"doi":"10.1109/ICETEMS66917.2026.11469202","date":"","title":"","authors":"","journal":"","logo":""}],"authors":[{"id":580295270,"identity":"6575d337-36bb-41d8-ba9f-b9838d3416b2","order_by":0,"name":"Vipul Razdan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvElEQVRIie3PoQrDMBCA4YRCVKC2fYuoqNI+yMyFQKf2BhWZmtmrzE4HClOjsYWa9g3mtpmxa2G6NzdYfnXiPo5jLBb7ydL7w7wKHPjeU43KRlHPxNFJPop2mWhEDR4UyFCeDi1eaYrNOunAA2SDPV8Nkku9c2skP+ILoAarPRLuWgpJuAPorA4TkaRSJAy8L3VPvZJKKZhxFnSPV4Dyi0DCn66sdNhO460p1skns2wCdX2u+mY5FovF/qw30WdE1oK3PdEAAAAASUVORK5CYII=","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Vipul","middleName":"","lastName":"Razdan","suffix":""}],"badges":[],"createdAt":"2026-01-26 05:51:51","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-8696862/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8696862/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107486622,"identity":"0811209b-90bc-4d6d-9593-117d1e5a8ec6","added_by":"auto","created_at":"2026-04-22 02:38:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":128720,"visible":true,"origin":"","legend":"","description":"","filename":"VectorSemanticsatScaleAnAIPipelineforFinancialTextSimilarity1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8696862/v1_covered_5c944e7e-584d-4d05-a893-d2561e209dd2.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eVector Semantics at Scale: An AI Pipeline for Financial Text Similarity\u003c/p\u003e","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":"Cosine similarity, TF-IDF, financial text mining, distributed computing, EDGAR, document clustering, natural language processing, accounting comparability","lastPublishedDoi":"10.21203/rs.3.rs-8696862/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8696862/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper presents an end-to-end AI system that transforms unstructured corporate filings into vector representations and computes interpretable similarity signals using tf-idf and cosine metrics within a distributed pipeline. The approach unifies robust preprocessing (token normalization, stemming/lemmatization) with scalable retrieval, parsing, and clustering, enabling comparative analysis of accounting policy narratives across firms and time. Extensive empirical evaluation quantifies how these similarity features relate to firm-level attributes and investor behavior, illustrating how classic NLP can yield actionable structure from financial disclosures at web scale. The design and experiments offer a reproducible blueprint for AI-driven text analytics in regulated domains, coupling information retrieval methods with cloud compute for high-throughput document understanding.\u003c/p\u003e","manuscriptTitle":"Vector Semantics at Scale: An AI Pipeline for Financial Text Similarity","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-29 12:21:20","doi":"10.21203/rs.3.rs-8696862/v1","editorialEvents":[{"type":"communityComments","content":1}],"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":"87a2b422-3e0b-46b0-b8c4-7c7e16eb72a0","owner":[],"postedDate":"January 29th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-29T12:21:20+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-29 12:21:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8696862","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8696862","identity":"rs-8696862","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}