Leverage Large Language Model with HyperGraph Augmentation for Data Imputation in the Retail industry

Leverage Large Language Model with HyperGraph Augmentation for Data Imputation in the Retail industry | 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 Leverage Large Language Model with HyperGraph Augmentation for Data Imputation in the Retail industry Ying Chai, ShaoZheng Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7727061/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 9 You are reading this latest preprint version Abstract The retail industry plays a critical role in the global economy, with comprehensive datasets being indispensable for informed decision-making in areas such as inventory management, pricing, and demand forecasting. However, due to inconsistent data collection, system failures, and external disruptions, it faces significant challenges related to missing data. The missing data imputation is particularly complex due to the heterogeneous nature of retail datasets, which encompass numerical, categorical, and textual information. Traditional imputation methods often struggle to capture the intricate, higher-order relationships inherent in such mixed-type datasets. To overcome these limitations, we propose a novel framework that integrates large language models (LLMs) with hypergraph-structured representations of tabular data. We propose the Hybrid Tabular-Cell Embedding Rank (HTERank) to model the heterogeneous interactions among the mixed-type data, and introduce random walks on the hypergraph to sample semantically relevant neighborhoods. Leveraging the in-context-learning ability, the LLM is equipped with the sampling neighborhoods to mitigate hallucinations and an ensemble-learning based voting mechanisms across multiple walks is deployed for reliable inference. Experiments on various real-world retailing datasets demonstrate the effectiveness and efficiency of our method. Notably, the proposed framework operates without extra fine-tuning, ensuring scalability in dynamic industrial environments. Data imputation Retail industry Large language model Hypergraph Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 31 Jan, 2026 Reviews received at journal 07 Jan, 2026 Reviewers agreed at journal 08 Dec, 2025 Reviews received at journal 02 Dec, 2025 Reviewers agreed at journal 21 Oct, 2025 Reviewers invited by journal 21 Oct, 2025 Editor assigned by journal 20 Oct, 2025 Submission checks completed at journal 27 Sep, 2025 First submitted to journal 27 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-7727061","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":532986414,"identity":"e29a2db2-68e2-451b-b986-52ffa39e0bd9","order_by":0,"name":"Ying Chai","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFUlEQVRIie3NMUvDQBTA8QsHyXIhg8sLhX6GCwFRhPar5AjERerQ5QaRKweXzTlC8TM4VdwuBOxyHyDQJcXVoS7SoaBNV03I6HB/Hjc87sdDyGb7hwXYWTQ7DmQq0fV+x1HSbqGPhLmUUWEuxtQTTViYAYSatTrzFY8pKZuRrwYQVDOFiAH2AmlC/adqRjUuNwRNZl3CKZhqgAN7LbIkCVfVnGo3vSIonXcRDCyn9HhF1DeJjlYb9qzJ+YggzUQHcYGp04j69lOwZUuCr15CSKngODE1OkWlOF1xewl4CxkJA+MwF5kj3r7ZY+XGl0uadpJp5W3fD/yeBBhl+HCXsYe13NYffNJJ/gi3Dx3+32az2Wy/+wEkKWP8CpPKEQAAAABJRU5ErkJggg==","orcid":"","institution":"Wuhan University","correspondingAuthor":true,"prefix":"","firstName":"Ying","middleName":"","lastName":"Chai","suffix":""},{"id":532986415,"identity":"88a5bfd1-f969-4586-8e9b-b408a327664b","order_by":1,"name":"ShaoZheng Wang","email":"","orcid":"","institution":"Wuhan Business University","correspondingAuthor":false,"prefix":"","firstName":"ShaoZheng","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-09-27 08:23:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7727061/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7727061/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94834546,"identity":"93081f3b-0f49-45f6-b0a7-c07329d2e9eb","added_by":"auto","created_at":"2025-10-31 08:08:04","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4563,"visible":true,"origin":"","legend":"","description":"","filename":"9097adda19664f4c9696f6b5998b86c7.json","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/20c3b7347474bfd8140edaf0.json"},{"id":94834548,"identity":"244c010c-afef-44dd-bb40-3358ac998cdb","added_by":"auto","created_at":"2025-10-31 08:08:04","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":122063,"visible":true,"origin":"","legend":"","description":"","filename":"9097adda19664f4c9696f6b5998b86c71enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/f898b7b441f3fab06252db21.xml"},{"id":94834547,"identity":"083ce7aa-c5da-4954-879d-d8853eb5a75d","added_by":"auto","created_at":"2025-10-31 08:08:04","extension":"eps","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2890,"visible":true,"origin":"","legend":"","description":"","filename":"empty.eps","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/059db9dce758e594312d1480.eps"},{"id":94834549,"identity":"d55b6187-13c6-4bfa-963a-df3a53ae04f3","added_by":"auto","created_at":"2025-10-31 08:08:04","extension":"eps","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91593,"visible":true,"origin":"","legend":"","description":"","filename":"fig.eps","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/49cff0adc7e48761e775e6d9.eps"},{"id":94834556,"identity":"58aa92b2-7cdd-43f3-bb33-249bc383b6ae","added_by":"auto","created_at":"2025-10-31 08:08:04","extension":"pdf","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":693858,"visible":true,"origin":"","legend":"","description":"","filename":"retailllmarxiv.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/9a580e0627fc8a13e5ee76d4.pdf"},{"id":94984844,"identity":"af83914b-a76e-433f-bca3-e07ca01a0208","added_by":"auto","created_at":"2025-11-03 06:56:35","extension":"bst","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/35086c705c4314f70bae923a.bst"},{"id":94834550,"identity":"1410248f-b3d1-4310-a2c2-e9519d72aa85","added_by":"auto","created_at":"2025-10-31 08:08:04","extension":"bst","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/1a8435eac1d57b6060050119.bst"},{"id":94834562,"identity":"7870eb12-bc84-4fa7-8a90-600953aea3c4","added_by":"auto","created_at":"2025-10-31 08:08:05","extension":"pdf","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":421391,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/6edbe3b7121336773290d2c3.pdf"},{"id":94984750,"identity":"39fa040c-7d1d-4691-aeb4-f978da0eaed4","added_by":"auto","created_at":"2025-11-03 06:55:53","extension":"bst","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/0fe664e5186a0500157fcbd4.bst"},{"id":94834553,"identity":"c4bf4cb1-59a9-4971-8434-88724b17de34","added_by":"auto","created_at":"2025-10-31 08:08:04","extension":"bst","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/b34ee48be94c859c120f8afc.bst"},{"id":94834552,"identity":"2158cfd2-9c53-45bd-bf52-88ec6015f09e","added_by":"auto","created_at":"2025-10-31 08:08:04","extension":"cls","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/0e9adb31b088e51bdd6f6013.cls"},{"id":94984715,"identity":"9cbd0326-cdfb-4f0d-b0bd-80ab89732007","added_by":"auto","created_at":"2025-11-03 06:55:32","extension":"bst","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/d08c73766eb001b68a5c6896.bst"},{"id":94984741,"identity":"ae4122df-0010-4a8a-aa80-1455b2134b41","added_by":"auto","created_at":"2025-11-03 06:55:47","extension":"bst","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/c3cff412976b291e1a3020c2.bst"},{"id":94834559,"identity":"81da5660-fc23-44a0-9ff4-2becb6963001","added_by":"auto","created_at":"2025-10-31 08:08:04","extension":"bst","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/ca58a65eb9e8f47914c2fd01.bst"},{"id":94984962,"identity":"2cf4675d-77a3-4400-89d6-776ace945ff0","added_by":"auto","created_at":"2025-11-03 06:57:02","extension":"bst","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/b57f5b6f0b2edb3d8a6f3d4e.bst"},{"id":94984723,"identity":"14b6beab-3883-4e6b-b1ed-f8e3153a46b8","added_by":"auto","created_at":"2025-11-03 06:55:38","extension":"bst","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/cbdb4694a1dd923537e7474d.bst"},{"id":94834565,"identity":"54b6cb24-7306-455b-bdfd-df69259f37c9","added_by":"auto","created_at":"2025-10-31 08:08:05","extension":"pdf","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":418495,"visible":true,"origin":"","legend":"","description":"","filename":"usermanual.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/751e3ac3ee151faf70f40e6b.pdf"},{"id":94834560,"identity":"b5a0cb47-d2ad-41c8-9604-b6bc34e6409a","added_by":"auto","created_at":"2025-10-31 08:08:05","extension":"xml","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":136731,"visible":true,"origin":"","legend":"","description":"","filename":"9097adda19664f4c9696f6b5998b86c71structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/d064ae7825f51ca4cd00d592.xml"},{"id":94834563,"identity":"354db61c-c567-4477-adee-9adfcd385bbf","added_by":"auto","created_at":"2025-10-31 08:08:05","extension":"html","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":142878,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1/60b568ad2a2c19eb2a27688d.html"},{"id":94990335,"identity":"586aad4f-5986-4a88-9d76-cffe704f7f4f","added_by":"auto","created_at":"2025-11-03 07:16:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":485708,"visible":true,"origin":"","legend":"","description":"","filename":"retailllmarxiv.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7727061/v1_covered_2566e182-4f2d-479c-863d-ef2c266406d6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Leverage Large Language Model with HyperGraph Augmentation for Data Imputation in the Retail industry","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":"international-journal-of-data-science-and-analytics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jdsa","sideBox":"Learn more about [International Journal of Data Science and Analytics](http://link.springer.com/journal/41060)","snPcode":"41060","submissionUrl":"https://submission.nature.com/new-submission/41060/3","title":"International Journal of Data Science and Analytics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Data imputation, Retail industry, Large language model, Hypergraph","lastPublishedDoi":"10.21203/rs.3.rs-7727061/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7727061/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe retail industry plays a critical role in the global economy, with comprehensive datasets being indispensable for informed decision-making in areas such as inventory management, pricing, and demand forecasting. However, due to inconsistent data collection, system failures, and external disruptions, it faces significant challenges related to missing data. The missing data imputation is particularly complex due to the heterogeneous nature of retail datasets, which encompass numerical, categorical, and textual information. Traditional imputation methods often struggle to capture the intricate, higher-order relationships inherent in such mixed-type datasets. To overcome these limitations, we propose a novel framework that integrates large language models (LLMs) with hypergraph-structured representations of tabular data. We propose the Hybrid Tabular-Cell Embedding Rank (HTERank) to model the heterogeneous interactions among the mixed-type data, and introduce random walks on the hypergraph to sample semantically relevant neighborhoods. Leveraging the in-context-learning ability, the LLM is equipped with the sampling neighborhoods to mitigate hallucinations and an ensemble-learning based voting mechanisms across multiple walks is deployed for reliable inference. Experiments on various real-world retailing datasets demonstrate the effectiveness and efficiency of our method. Notably, the proposed framework operates without extra fine-tuning, ensuring scalability in dynamic industrial environments.\u003c/p\u003e","manuscriptTitle":"Leverage Large Language Model with HyperGraph Augmentation for Data Imputation in the Retail industry","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-31 08:08:00","doi":"10.21203/rs.3.rs-7727061/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-31T15:54:13+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-08T03:19:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"325139483553909340512876800047634243213","date":"2025-12-09T02:50:39+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-02T22:58:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"126038202741333958977626493395124171922","date":"2025-10-21T17:36:01+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-21T15:44:12+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-20T09:01:29+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-27T10:23:40+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Data Science and Analytics","date":"2025-09-27T08:10:25+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-data-science-and-analytics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jdsa","sideBox":"Learn more about [International Journal of Data Science and Analytics](http://link.springer.com/journal/41060)","snPcode":"41060","submissionUrl":"https://submission.nature.com/new-submission/41060/3","title":"International Journal of Data Science and Analytics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"648e0a16-1464-4752-af90-53c287a65046","owner":[],"postedDate":"October 31st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-01-31T16:08:23+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-31 08:08:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7727061","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7727061","identity":"rs-7727061","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}