A Quantum Neural Network for Fraud Detection Using a Data-Driven Priority Entanglement Scheme

A Quantum Neural Network for Fraud Detection Using a Data-Driven Priority Entanglement Scheme | 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 Quantum Neural Network for Fraud Detection Using a Data-Driven Priority Entanglement Scheme Yousaf Khaliq, Donglin Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7991330/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 study investigates whether a variational quantum circuit can improve minority-class sensitivity when substituted for a single dense layer in a strong neural network baseline for credit-card fraud detection. Under matched parameter budgets and identical preprocessing, we evaluate a hybrid quantum–classical model against classical baselines on the Kaggle dataset, preserving all 492 fraud cases and downsampling legitimate transactions to 10,000. Our hybrid employs data re-uploading to expose all 30 features with 10–15 qubits. It introduces a data-driven priority-entanglement scheme that couples the most dependent feature pairs before a strongly entangling block. Across 100 (10-qubit) and 20 (15-qubit) randomized runs, the hybrid achieves meaningful and consistent gains in recall and PR-AUC over tuned classical models (e.g., PR-AUC 0.9229±0.006 at 15q/1-layer/10 priority pairs vs 0.9150±0.014 for logistic regression; recall +0.047 over the best classical result).Performance peaks at moderate entanglement budgets, beyond which deeper circuits only exacerbate a precision-recall trade-off, revealing an underlying trainability limit. Results indicate that correlation-guided entanglement provides a useful inductive bias that modestly improves fraud detection under strict capacity parity. Quantum Machine Learning Quantum Neural Network Classifier Fraud Detection Custom Entanglement 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-7991330","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":546422268,"identity":"2831da48-0d6a-4144-9465-7950e7caea9b","order_by":0,"name":"Yousaf Khaliq","email":"","orcid":"","institution":"Middle Tennessee State University","correspondingAuthor":false,"prefix":"","firstName":"Yousaf","middleName":"","lastName":"Khaliq","suffix":""},{"id":546422269,"identity":"baf0985f-d539-48b4-b94e-e562324fcd2a","order_by":1,"name":"Donglin Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAsklEQVRIiWNgGAWjYDCCAyCiAsrhIV7LGQYJErUwtpGihe9G8rOHX+dtq5OfkcD44G0bEVokb6SZG8tuuy1hcCOB2XAuMVoMbieYSUuCtEgksEnzEqcl/Zu05JzbEkCHsf8mUkuOmeTHhtsSDDcS2JiJ0iJ5/02ZNMOx25IbzjxslpxzjggtfGeOb5P8UXObX749+eCHN2VEaAEBZkh0MDYQqR6k9gfxakfBKBgFo2AkAgCpbTic6KweMAAAAABJRU5ErkJggg==","orcid":"","institution":"Middle Tennessee State University","correspondingAuthor":true,"prefix":"","firstName":"Donglin","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-10-30 16:23:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7991330/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7991330/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96252055,"identity":"686df368-0665-4844-9d27-9ab5d9286be7","added_by":"auto","created_at":"2025-11-19 07:40:24","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4184,"visible":true,"origin":"","legend":"","description":"","filename":"523bdb6e979f49049e59ba4480cc6607.json","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/23ba78dace6ba296494476b3.json"},{"id":96198198,"identity":"8ab818dc-52d5-47db-b9de-1b0fff28dc58","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"png","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35468,"visible":true,"origin":"","legend":"","description":"","filename":"QNNArch.png","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/1508d18834f8798908ccdf76.png"},{"id":96198200,"identity":"d6347f81-df23-4cd8-aad6-1c57c03d3e62","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"png","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96679,"visible":true,"origin":"","legend":"","description":"","filename":"QNNcircuit.png","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/0c249bd4e8a74e728015ac3b.png"},{"id":96198196,"identity":"4b51fa60-fe4d-44d3-b7d1-68ed78874bd0","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30527,"visible":true,"origin":"","legend":"","description":"","filename":"SEL.png","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/579972f27275507a4b973d36.png"},{"id":96198199,"identity":"9867278b-535d-432b-9839-834908d4a05b","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25261,"visible":true,"origin":"","legend":"","description":"","filename":"classimbalance.png","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/513bf8f32adb1a679d46df27.png"},{"id":96198201,"identity":"b8508ded-67e0-408c-8f6f-773f4a6f3d8f","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"pdf","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":426887,"visible":true,"origin":"","legend":"","description":"","filename":"quantumneuralnetworkonfraud.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/775403af169ac5800e374615.pdf"},{"id":96198204,"identity":"8dd3cfc4-8b1a-4ffa-b15d-f76b8db4c7c6","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"bst","order_by":6,"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-7991330/v1/c5a582a408abf6624a10085a.bst"},{"id":96198202,"identity":"de37ff27-ea3b-4aaf-aa49-39bd329a9903","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"bst","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40398,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/39f84459d30708a8dcac1e4a.bst"},{"id":96198209,"identity":"20ac282f-1b6d-4005-a4ee-40a5918f49c1","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"cls","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55955,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/9988046536d134ea57b25227.cls"},{"id":96252805,"identity":"c8cdd858-2174-485d-8038-ce31c26424a6","added_by":"auto","created_at":"2025-11-19 07:41:29","extension":"bst","order_by":9,"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-7991330/v1/7d88bd923cff2faa6d85dac1.bst"},{"id":96250394,"identity":"b85eebe3-5a6a-4e28-8aab-ab6f6ea99c39","added_by":"auto","created_at":"2025-11-19 07:38:15","extension":"bst","order_by":10,"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-7991330/v1/84937c1822aae8417fb6219b.bst"},{"id":96198203,"identity":"c9241721-5dea-4bc3-b35a-c2bfe7f95094","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"bst","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64141,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphys.bst","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/0423773c2145ea95c570a2ac.bst"},{"id":96198211,"identity":"6dcaa5c7-a55a-484b-a1ba-07250d1da315","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16256,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineQNNArch.png","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/3a7fe5f528f55ce0a79e68bb.png"},{"id":96198207,"identity":"2f22700a-d903-4397-b66b-0af91e141efb","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33249,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineQNNcircuit.png","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/6f16db416345c1a8e0e6ea4b.png"},{"id":96198208,"identity":"213ed300-52c8-4018-8d15-79b96c1034d1","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25624,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineSEL.png","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/616ee8c70e97ae28cc62c0d7.png"},{"id":96198212,"identity":"aca5d38a-381f-4e27-9952-94070d347d5d","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21752,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineclassimbalance.png","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/f96ad1df315d27e525ceb06b.png"},{"id":96198213,"identity":"dd7f69a8-e572-41da-96dd-c9ac02b297b5","added_by":"auto","created_at":"2025-11-18 15:51:02","extension":"xml","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96341,"visible":true,"origin":"","legend":"","description":"","filename":"523bdb6e979f49049e59ba4480cc66071structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1/2017ffeb292001308bae30a9.xml"},{"id":109054009,"identity":"3a8143af-1022-4c94-9683-e1da9e8a8cf5","added_by":"auto","created_at":"2026-05-12 07:16:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":330434,"visible":true,"origin":"","legend":"","description":"","filename":"quantumneuralnetworkonfraud.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7991330/v1_covered_4de2d9ed-5c84-46fd-b42a-58222e8a3ca8.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Quantum Neural Network for Fraud Detection Using a Data-Driven Priority Entanglement Scheme","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":"Quantum Machine Learning, Quantum Neural Network Classifier, Fraud Detection, Custom Entanglement","lastPublishedDoi":"10.21203/rs.3.rs-7991330/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7991330/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\n\nThis study investigates whether a variational quantum circuit can improve\nminority-class sensitivity when substituted for a single dense layer in a strong neural network baseline for credit-card fraud detection. Under matched parameter budgets and identical preprocessing, we evaluate a hybrid quantum–classical model against classical baselines on the Kaggle dataset, preserving all 492 fraud cases and downsampling legitimate transactions to 10,000. Our hybrid employs data re-uploading to expose all 30 features with 10–15 qubits. It introduces a data-driven priority-entanglement scheme that couples the most dependent feature pairs before a strongly entangling block. Across 100 (10-qubit) and 20 (15-qubit) randomized runs, the hybrid achieves meaningful and consistent gains in recall and PR-AUC over tuned classical models (e.g., PR-AUC 0.9229±0.006 at 15q/1-layer/10 priority pairs vs 0.9150±0.014 for logistic regression; recall +0.047 over the best classical result).Performance peaks at moderate entanglement budgets, beyond which deeper circuits only exacerbate a precision-recall trade-off, revealing an underlying trainability limit. Results indicate that correlation-guided entanglement provides a useful inductive bias that modestly improves fraud detection under strict capacity parity.\n","manuscriptTitle":"A Quantum Neural Network for Fraud Detection Using a Data-Driven Priority Entanglement Scheme","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-18 15:50:57","doi":"10.21203/rs.3.rs-7991330/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":"7ccb2c91-3f47-40b8-a9a3-8431590a9a5f","owner":[],"postedDate":"November 18th, 2025","published":true,"recentEditorialEvents":[{"type":"decision","content":"Withdrawn","date":"2026-05-12T06:56:09+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-12T07:13:28+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-18 15:50:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7991330","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7991330","identity":"rs-7991330","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}