A Deep Learning Hybrid RNN-LSTM Model for Credit Card Fraud Detection

A Deep Learning Hybrid RNN-LSTM Model for Credit Card Fraud Detection | 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 A Deep Learning Hybrid RNN-LSTM Model for Credit Card Fraud Detection Hongfang Zhou, Xinhao Zheng, Jiajia Du This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8327749/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 To address the limitation that traditional classification models perform poorly when faced with highly imbalanced data in credit card fraud detection, this paper puts forward a joint model that integrates a Recurrent Neural Network - Long Short - Term Memory (RNN - LSTM) architecture with a hybrid sampling strategy. By conducting a systematic analysis of the category distribution characteristics of real transaction datasets and combining with over-sampling or under-sampling data balance processing, a deep neural network capable of learning temporal dependencies is established. Experimental results demonstrate that the optimized RNN - LSTM model achieves breakthrough performance on the publicly available EU credit card transaction dataset. Compared with traditional classifiers such as K - Nearest Neighbors (KNN), AdaBoost, and the standalone LSTM model, the proposed approach improves the F1 - score by 5.31% (reaching 0.8544), maintains an overall accuracy of 99.96%, and achieves a fraud recall rate of 80.56%, effectively balancing the crucial trade - off between false alarm control and positive sample identification. Furthermore, multidimensional performance comparisons show that the proposed approach outperforms the benchmark models in precision (84.12%) and the Area Under the Curve (AUC) value (0.932), validating the synergistic effect of structural optimization and the hybrid sampling strategy. This study provides a solution with both theoretical and practical significance for financial risk prevention and control. Moreover, the proposed methodological framework can be extended to anomaly detection tasks involving other types of imbalanced time - series data. Credit card Fraud detection Ensemble learning Full Text Additional Declarations No competing interests reported. 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-8327749","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":566517759,"identity":"01dbd7dc-6d3f-466e-9717-5b9394001d8f","order_by":0,"name":"Hongfang Zhou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxklEQVRIiWNgGAWjYDACCQYGZgYbGyiPjWgtaWkMIIokLYdJ0CI/u/mYdEHC+cT+GfkHGD6UHWbgn92AXwvjnGNp0jMSbhtL3EhmYJxx7jCDxJ0D+LUwS+SYSfP+uC3HANTCzNt2mMFAIgG/FjaQFp6EczzyIC1/idHCA9FyQM4ApIWRGC0SEmnJ1jwJycaGZx4bHOw5l84jcYOAFvkZyQdv8yTYJc47nvjwwY8yazn+GQS0oIADIJeSoH4UjIJRMApGAS4AAKc0OsiLPNETAAAAAElFTkSuQmCC","orcid":"","institution":"Xi'an University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Hongfang","middleName":"","lastName":"Zhou","suffix":""},{"id":566517760,"identity":"3aa2caf2-05b6-471d-8c17-0ed917f7ce3a","order_by":1,"name":"Xinhao Zheng","email":"","orcid":"","institution":"Xi'an University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Xinhao","middleName":"","lastName":"Zheng","suffix":""},{"id":566517761,"identity":"990adedf-65ff-4bbb-8e3c-02ab87362814","order_by":2,"name":"Jiajia Du","email":"","orcid":"","institution":"Xi'an University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jiajia","middleName":"","lastName":"Du","suffix":""}],"badges":[],"createdAt":"2025-12-10 12:54:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8327749/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8327749/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":99316506,"identity":"a4f2c072-d6f9-4d74-8033-411a522b8fb5","added_by":"auto","created_at":"2025-12-31 16:28:32","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":821272,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/5c8207712e82e659bb5bbd95.docx"},{"id":99314869,"identity":"34319577-b913-47f9-8a7c-7ee73776573c","added_by":"auto","created_at":"2025-12-31 16:24:19","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5662,"visible":true,"origin":"","legend":"","description":"","filename":"866ab3fd608f4cccb69ac8cf2c42033b.json","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/0821e1489596fac9864baff9.json"},{"id":99314966,"identity":"72451ce9-343e-4e33-af4f-3d7f4f329c01","added_by":"auto","created_at":"2025-12-31 16:25:13","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11209,"visible":true,"origin":"","legend":"","description":"","filename":"DeclarationofInterestStatement.docx","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/7bddcb54f94adc56980a2182.docx"},{"id":99133985,"identity":"80e75096-d9aa-4764-80f0-3f51bd803db1","added_by":"auto","created_at":"2025-12-29 06:06:35","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":134484,"visible":true,"origin":"","legend":"","description":"","filename":"866ab3fd608f4cccb69ac8cf2c42033b1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/75e9864a0c0dc86fb5dbaddb.xml"},{"id":99134001,"identity":"db0ba3d3-39e2-428a-94fc-29916ea58acc","added_by":"auto","created_at":"2025-12-29 06:06:35","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":450061,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/9905513a5503d31de052f50e.png"},{"id":99133983,"identity":"775831d6-bc12-44ec-9229-8cc554b8d5e0","added_by":"auto","created_at":"2025-12-29 06:06:35","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":66993,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/d4126eba4b409a9f26c6fcd0.png"},{"id":99133982,"identity":"90893ff4-0b4b-4f32-b85c-20db4d7ac4bb","added_by":"auto","created_at":"2025-12-29 06:06:35","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":53618,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/8a2b0aaaba9440dfd9e1b1da.png"},{"id":99788218,"identity":"b7c323ea-d376-4f9a-842f-fb0ee2fb2a66","added_by":"auto","created_at":"2026-01-08 12:45:42","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":47052,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/5d17a62ac663a8ae6b27cb0f.png"},{"id":99316968,"identity":"01ae3f50-9e9f-4f07-bfd6-3b444e6cc097","added_by":"auto","created_at":"2025-12-31 16:29:30","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49930,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/f5fe49b98b16e5be5af74d2a.png"},{"id":99315845,"identity":"fa6214a4-767d-4d86-8b88-6cb05bbcca7f","added_by":"auto","created_at":"2025-12-31 16:27:23","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32093,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/fbf9461fde7a0a8b658e25fa.png"},{"id":99316523,"identity":"2d9b55ea-1077-4575-a707-be5ed9c621af","added_by":"auto","created_at":"2025-12-31 16:28:33","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55858,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/977005c39b0c127b3c65742b.png"},{"id":99315785,"identity":"bb45f672-3d7c-4753-9478-95c60b7eeac2","added_by":"auto","created_at":"2025-12-31 16:27:21","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35245,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/837778132c752ed29d1dd488.png"},{"id":99133988,"identity":"7e44ddff-a053-403d-af58-48a75105e3a6","added_by":"auto","created_at":"2025-12-29 06:06:35","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55858,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/fe3d08d1a1d4c55b7d23b33d.png"},{"id":99314934,"identity":"22aaf0b7-1510-42d6-88be-2f4cb1ad149b","added_by":"auto","created_at":"2025-12-31 16:24:55","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21182,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/b5af3773c521e07f86aba47a.png"},{"id":99133991,"identity":"d5a15fa0-0a7d-4aa8-91ff-e7ad0ba7bd0e","added_by":"auto","created_at":"2025-12-29 06:06:35","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15287,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/52544587a979be212179b76a.png"},{"id":99134003,"identity":"d8691862-1ced-40fc-a066-89181544987b","added_by":"auto","created_at":"2025-12-29 06:06:35","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16271,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/f2cb13034a3482e2e0734d13.png"},{"id":99314842,"identity":"7dd9c7a7-622d-475b-8f45-2bee752cbd0b","added_by":"auto","created_at":"2025-12-31 16:23:43","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10353,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/a70446bd37f2fb4d0a348531.png"},{"id":99134002,"identity":"de921088-8a36-4269-b81c-135550e41b4a","added_by":"auto","created_at":"2025-12-29 06:06:35","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7562,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/70e360ef221ff1a62eee23c1.png"},{"id":99316755,"identity":"7cf679e6-046f-401c-a93f-e0f532a919b2","added_by":"auto","created_at":"2025-12-31 16:29:08","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7451,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/a09a6091e124aa0fce04a2aa.png"},{"id":99314895,"identity":"53ca1508-68b2-4880-9b41-96fb436cdbae","added_by":"auto","created_at":"2025-12-31 16:24:21","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14548,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/70b3d41771cd3be0196f3c57.png"},{"id":99314888,"identity":"35af066f-8146-4d28-a055-cc2890215b20","added_by":"auto","created_at":"2025-12-31 16:24:21","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6232,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/dbcb1361dfb15d1c11153265.png"},{"id":99134000,"identity":"a774462b-6bcc-4007-ac55-99a124b004b1","added_by":"auto","created_at":"2025-12-29 06:06:35","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14548,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/d94294665b3c01d072958a16.png"},{"id":99134005,"identity":"4a5aceab-f3ef-475e-b8cc-26c84ac57627","added_by":"auto","created_at":"2025-12-29 06:06:35","extension":"xml","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":133549,"visible":true,"origin":"","legend":"","description":"","filename":"866ab3fd608f4cccb69ac8cf2c42033b1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/18618f7599d5defe8980f408.xml"},{"id":99134006,"identity":"f3f49510-7f0d-4a84-b14b-57b9d2ff757c","added_by":"auto","created_at":"2025-12-29 06:06:35","extension":"html","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146295,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1/26d7fce0e7407e3028b6d22b.html"},{"id":109480114,"identity":"4c6e591b-db59-48f8-a140-86ca8b7205e4","added_by":"auto","created_at":"2026-05-18 14:55:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":667482,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8327749/v1_covered_c2e301d7-3f06-4736-9f6d-724b81496787.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Deep Learning Hybrid RNN-LSTM Model for Credit Card Fraud Detection","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Credit card, Fraud detection, Ensemble learning","lastPublishedDoi":"10.21203/rs.3.rs-8327749/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8327749/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTo address the limitation that traditional classification models perform poorly when faced with highly imbalanced data in credit card fraud detection, this paper puts forward a joint model that integrates a Recurrent Neural Network - Long Short - Term Memory (RNN - LSTM) architecture with a hybrid sampling strategy. By conducting a systematic analysis of the category distribution characteristics of real transaction datasets and combining with over-sampling or under-sampling data balance processing, a deep neural network capable of learning temporal dependencies is established. Experimental results demonstrate that the optimized RNN - LSTM model achieves breakthrough performance on the publicly available EU credit card transaction dataset. Compared with traditional classifiers such as K - Nearest Neighbors (KNN), AdaBoost, and the standalone LSTM model, the proposed approach improves the F1 - score by 5.31% (reaching 0.8544), maintains an overall accuracy of 99.96%, and achieves a fraud recall rate of 80.56%, effectively balancing the crucial trade - off between false alarm control and positive sample identification. Furthermore, multidimensional performance comparisons show that the proposed approach outperforms the benchmark models in precision (84.12%) and the Area Under the Curve (AUC) value (0.932), validating the synergistic effect of structural optimization and the hybrid sampling strategy. This study provides a solution with both theoretical and practical significance for financial risk prevention and control. Moreover, the proposed methodological framework can be extended to anomaly detection tasks involving other types of imbalanced time - series data.\u003c/p\u003e","manuscriptTitle":"A Deep Learning Hybrid RNN-LSTM Model for Credit Card Fraud Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-29 06:06:30","doi":"10.21203/rs.3.rs-8327749/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":"d3791da4-1e9c-49e7-a7fd-4075102c014a","owner":[],"postedDate":"December 29th, 2025","published":true,"recentEditorialEvents":[{"type":"decision","content":"Rejected","date":"2026-05-18T14:45:34+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-18T14:55:36+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-29 06:06:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8327749","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8327749","identity":"rs-8327749","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}