High-Recall Deep Learning: A Gated Recurrent Unit Approach to Bank Account Fraud Detection on Imbalanced Data

High-Recall Deep Learning: A Gated Recurrent Unit Approach to Bank Account Fraud Detection on Imbalanced Data | 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 High-Recall Deep Learning: A Gated Recurrent Unit Approach to Bank Account Fraud Detection on Imbalanced Data Wenxi Sun, Zhichun Qi, Qiannan Shen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8136120/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 Fraud detection in financial services is challenged by severe class imbalance, where fraudulent events are rare. This study provides a rigorous comparison of classical machine learning models—Logistic Regression, SVM, Random Forest, and LightGBM—and a Gated Recurrent Unit (GRU) deep learning model on a large-scale, imbalanced bank account fraud dataset. Our findings reveal a dramatic performance divide. All classical models, including the widely-used tree-based ensembles, proved ineffective at the primary detection task, with fraud recall scores below 7%.In stark contrast, the GRU network successfully identified the vast majority of fraudulent cases, achieving over 78% recall on the minority fraud class, albeit at the cost of very low precision. The results demonstrate that the GRU offers a viable, high-recall solution where classical models fail. This highlights a critical strategic choice for financial institutions: adopt a high-recall/high-alert detection framework or use conventional models that allow most fraud to go undetected. The approach is broadly applicable across financial domains—including banking and insurance—where rare-event detection is critical. Artificial Intelligence and Machine Learning Supervised Learning Fraud Detection Class Imbalance Deep Learning Gated Recurrent Unit (GRU) Precision-Recall Trade-off Tabular Data Full Text Additional Declarations The authors declare no competing interests. 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-8136120","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":546335563,"identity":"17d878ec-e278-4dff-8211-cce3023a8d1c","order_by":0,"name":"Wenxi Sun","email":"","orcid":"","institution":"Johns Hopkins University","correspondingAuthor":false,"prefix":"","firstName":"Wenxi","middleName":"","lastName":"Sun","suffix":""},{"id":546335564,"identity":"b25e0075-8115-4665-8d7d-995f6df630cc","order_by":1,"name":"Zhichun Qi","email":"","orcid":"","institution":"The George Washington University","correspondingAuthor":false,"prefix":"","firstName":"Zhichun","middleName":"","lastName":"Qi","suffix":""},{"id":546335562,"identity":"62b000cd-8529-4a85-beb1-f5dce54787f4","order_by":2,"name":"Qiannan Shen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAnUlEQVRIiWNgGAWjYBACNiBmZqg4AGIbkKLlDClaQICZsY0ULXzspxNvF867k9jA3rxNgjiH8eRutp657VliA8+xMiK1MORuk+bddjixQSLHjEgt/G+BWuYAtci/IVaLBMiWBpAtPERrebvZesaxZ8ZtPGnFFkRpke/P3Xi7oOaObD/74Y03iNICAmD3sBGtHK5lFIyCUTAKRgFOAAAu9iyAZMqcmwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0009-0007-9492-1773","institution":"Boston University","correspondingAuthor":true,"prefix":"","firstName":"Qiannan","middleName":"","lastName":"Shen","suffix":""}],"badges":[],"createdAt":"2025-11-17 13:43:59","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8136120/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8136120/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":99315680,"identity":"1b0f0e52-3843-4423-8ee0-59f5c8ca4a3c","added_by":"auto","created_at":"2025-12-31 16:27:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":470119,"visible":true,"origin":"","legend":"","description":"","filename":"DSInSV1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8136120/v1_covered_53c9965e-b311-4a71-87b2-734dd86f4e54.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eHigh-Recall Deep Learning: A Gated Recurrent Unit Approach to Bank Account Fraud Detection on Imbalanced Data\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Johns Hopkins University","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":"Supervised Learning, Fraud Detection, Class Imbalance, Deep Learning, Gated Recurrent Unit (GRU), Precision-Recall Trade-off, Tabular Data","lastPublishedDoi":"10.21203/rs.3.rs-8136120/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8136120/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFraud detection in financial services is challenged by severe class imbalance, where fraudulent events are rare. This study provides a rigorous comparison of classical machine learning models—Logistic Regression, SVM, Random Forest, and LightGBM—and a Gated Recurrent Unit (GRU) deep learning model on a large-scale, imbalanced bank account fraud dataset. Our findings reveal a dramatic performance divide. All classical models, including the widely-used tree-based ensembles, proved ineffective at the primary detection task, with fraud recall scores below 7%.In stark contrast, the GRU network successfully identified the vast majority of fraudulent cases, achieving over 78% recall on the minority fraud class, albeit at the cost of very low precision. The results demonstrate that the GRU offers a viable, high-recall solution where classical models fail. This highlights a critical strategic choice for financial institutions: adopt a high-recall/high-alert detection framework or use conventional models that allow most fraud to go undetected. The approach is broadly applicable across financial domains—including banking and insurance—where rare-event detection is critical.\u003c/p\u003e","manuscriptTitle":"High-Recall Deep Learning: A Gated Recurrent Unit Approach to Bank Account Fraud Detection on Imbalanced Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-19 06:19:25","doi":"10.21203/rs.3.rs-8136120/v1","editorialEvents":[{"type":"communityComments","content":0}],"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":"b9ca4f3d-b07b-45de-8cc3-674d06947a11","owner":[],"postedDate":"November 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":58117859,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-11-19T06:19:25+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-19 06:19:25","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8136120","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8136120","identity":"rs-8136120","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}