The Decline of Synthetic Oversampling in Large-Scale Imbalanced Learning:A Post-SMOTE Empirical and Theoretical Study (2020–2025)

preprint OA: closed
Full text JSON View at publisher
Full text 38,982 characters · extracted from preprint-html · click to expand
The Decline of Synthetic Oversampling in Large-Scale Imbalanced Learning:A Post-SMOTE Empirical and Theoretical Study (2020–2025) | 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 The Decline of Synthetic Oversampling in Large-Scale Imbalanced Learning:A Post-SMOTE Empirical and Theoretical Study (2020–2025) Someyo kamal Utsho This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8236211/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 For over twenty years, SMOTE has been the standard default for addressing class imbalance. Yet a striking paradox has emerged: while researchers continue citing SMOTE extensively, practitioners have largely abandoned it in production systems. To understand this disconnect, we conducted a large-scale empirical and theoretical study of 821 papers published between 2020–2025, revealing a fundamental paradigm shift. Approximately 30% of new solutions now employ Generative AI (Diffusion Models), 30% rely on cost-sensitive loss functions, while the remainder explore hybrid approaches. We mathematically show why SMOTE fails at modern scales: its O ( N 2 ) complexity exhausts memory on billion-sample datasets, its nearest-neighbor logic distorts high-dimensional manifolds, and its CPU-bound design is incompatible with GPU pipelines. Beyond theory, we identify the novel “SMOTE Paradox”—the critical divergence between academic citations and real-world deployment. This systematic study maps the emerging post-SMOTE landscape, syn- thesizes theoretical foundations across three competing paradigms, and provides decision rules for practitioners. Empirically, we validate these findings on real-world fraud data (N = 284,807, im- balance 578:1), confirming that cost-sensitive learning achieves parity with oversampling (+ 0.29% F1-score improvement) while eliminating preprocessing overhead. Our contributions include: (1) quantitative documentation of the paradigm shift through systematic analysis, (2) mathematical proofs of SMOTE’s failure modes, (3) the novel SMOTE Paradox framework, and (4) empirical validation on production-scale data. We conclude with actionable guidelines for practitioners and identify two critical open problems for future research in large-scale imbalanced learning. Class imbalance SMOTE Diffusion models Cost-sensitive learning Systematic review 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-8236211","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":553252872,"identity":"d6518ee4-c956-4039-96c7-3969daed8387","order_by":0,"name":"Someyo kamal Utsho","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABC0lEQVRIie2PMUvEMBiGG29t90qH/gJBKWSq7Q9xaQjU5QqOGW5oOfg6iHsH/4KDCHGNFJyiWQO3GG516HjgYnrTLe3dKJgHAu8H38Obz/Mcjr9LYd+i7ncstQE14kQFNVtPlmOoT1bWCYJ+P84qcXtPtj4r44v2DaI7qbKntrctq/RmSrmUHy+JL5dXXBKIOrahNljlvazqKSWseBQAQ1wQCH25oVhYBdX9pBJ31euPVXKuDIQBfFKszLzi6YovAlgSrsk6CUBkWB9pGW85f5Ql5do0ppO0wNq2FDO3xO3D8/DN6DVXVIiBZTlWt+ZrWKXTH7Oc+QcD2W8WM+sjaHcw5EeWHQ6H4x/yC762b7NE/ENoAAAAAElFTkSuQmCC","orcid":"","institution":"University of Technology Malaysia","correspondingAuthor":true,"prefix":"","firstName":"Someyo","middleName":"kamal","lastName":"Utsho","suffix":""}],"badges":[],"createdAt":"2025-11-29 10:08:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8236211/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8236211/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97251235,"identity":"d0f08e10-27e2-497a-bb76-17f0327c211d","added_by":"auto","created_at":"2025-12-02 13:16:28","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":506446,"visible":true,"origin":"","legend":"","description":"","filename":"drafdmkd.docx","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/1e4dac5a6cf39948eda8c4eb.docx"},{"id":97229236,"identity":"3473a2d9-e515-4230-b2e2-a2fd3b0b6956","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4052,"visible":true,"origin":"","legend":"","description":"","filename":"6d75a00905204fceb244566cf3ba90a7.json","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/bc76e527f341f6272ef85fd6.json"},{"id":97229242,"identity":"95de8511-ec65-4be2-8f40-4659b357fa17","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":110379,"visible":true,"origin":"","legend":"","description":"","filename":"6d75a00905204fceb244566cf3ba90a71enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/63e40b9725312220abe66a0a.xml"},{"id":97229237,"identity":"f6edf086-f70a-471a-bbdb-80f7d5d64046","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"eps","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":48706,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage2.eps","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/83b1d3994bde90d35af4d03a.eps"},{"id":97229238,"identity":"3cc1986d-3c2b-410b-b279-47829c7a00d2","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"eps","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":393,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage4.eps","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/d5c544d40b3254b41c0154f8.eps"},{"id":97229246,"identity":"99556c69-4461-470f-9d02-0968ba35a76e","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1603,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/8d00389490fa1031ded616b7.jpeg"},{"id":97229249,"identity":"f0efb933-de2f-4386-9073-d10cecfa3462","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":310743,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/c855b97bcccfb36efd0130f1.jpeg"},{"id":97250641,"identity":"afa8f21e-94fa-452b-9f96-1a5e97f21e2a","added_by":"auto","created_at":"2025-12-02 13:14:51","extension":"jpeg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":82415,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/18f1fb48d228384e242897e4.jpeg"},{"id":97250266,"identity":"e42aa4cd-730e-4503-8c56-903e15c40bdf","added_by":"auto","created_at":"2025-12-02 13:14:11","extension":"jpeg","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26852,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage12.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/f8283b9a46ebc414ced98857.jpeg"},{"id":97250357,"identity":"b179a03b-fd5c-4615-a1f0-7e299273b47d","added_by":"auto","created_at":"2025-12-02 13:14:21","extension":"jpeg","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":61147,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage13.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/39951f3479b2e37d523ddeea.jpeg"},{"id":97229258,"identity":"d5da94b5-e38c-4392-9cc2-21842bebebfc","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"jpeg","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":220344,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage14.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/3e05a6b34ffae3b4217c1fa5.jpeg"},{"id":97250761,"identity":"88775961-db17-4741-8899-40b88355d781","added_by":"auto","created_at":"2025-12-02 13:15:10","extension":"jpeg","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4767,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage15.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/a80071018468fa416089c10d.jpeg"},{"id":97229264,"identity":"246f38cc-a14c-41a9-bc53-b8557df53b7e","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"jpeg","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":156980,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage16.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/77dc0b08a91661274bb0c991.jpeg"},{"id":97250591,"identity":"829aafec-3584-4d22-9b0d-af43fd1d169f","added_by":"auto","created_at":"2025-12-02 13:14:47","extension":"jpeg","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":189055,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage17.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/2809d901a2b58208b183e00c.jpeg"},{"id":97250567,"identity":"8f4ca39c-819f-441c-a485-aa90e6bab149","added_by":"auto","created_at":"2025-12-02 13:14:42","extension":"jpeg","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1074,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage18.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/7e9511138e00e5816179912b.jpeg"},{"id":97229251,"identity":"f8a9608e-96a3-4101-8da2-dd36a3a93b20","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"jpeg","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":217376,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage19.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/a93e0418f8770cf34d5a6abe.jpeg"},{"id":97251385,"identity":"a4382497-cc54-452f-9b3c-80c1b4f565d7","added_by":"auto","created_at":"2025-12-02 13:17:20","extension":"jpeg","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1074,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage18.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/4509530824776ab0576e8805.jpeg"},{"id":97251189,"identity":"286e6855-d182-49c4-9e12-8a0b9b99e7e7","added_by":"auto","created_at":"2025-12-02 13:16:20","extension":"jpeg","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1074,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage18.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/e63562e84505193875352ab3.jpeg"},{"id":97250488,"identity":"e805f497-496a-4eec-8c2c-e19bb56aa83e","added_by":"auto","created_at":"2025-12-02 13:14:36","extension":"jpeg","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":211696,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage21.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/1105a0a612f1b343d788093c.jpeg"},{"id":97251199,"identity":"f84cec59-1d7e-4a51-9b61-d2196ae3589b","added_by":"auto","created_at":"2025-12-02 13:16:22","extension":"jpeg","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":69308,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage22.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/ff4b0ca7fd0cfaa10a9c03cd.jpeg"},{"id":97250525,"identity":"854550f9-407c-433a-94ff-7cf5570377f4","added_by":"auto","created_at":"2025-12-02 13:14:39","extension":"jpeg","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":100036,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage23.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/046bd37942e2b57ba556b24e.jpeg"},{"id":97250329,"identity":"e2fff5c3-7589-4c50-955d-35748accd8f5","added_by":"auto","created_at":"2025-12-02 13:14:16","extension":"jpeg","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":72647,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage24.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/36f17944d6af309373ae5785.jpeg"},{"id":97250268,"identity":"9aa3c6fd-a4e5-4abf-aa1d-de4c4ee57eef","added_by":"auto","created_at":"2025-12-02 13:14:11","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":202,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage25.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/bcd9e1fe162336c343d3daea.png"},{"id":97250219,"identity":"41aa59ec-ccb2-4cf6-b594-62d3b0304e79","added_by":"auto","created_at":"2025-12-02 13:14:07","extension":"jpeg","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41308,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage26.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/0e56cfb3ae4431e85bec4bd0.jpeg"},{"id":97229269,"identity":"64994a34-996c-422f-8bf5-cb9514d0b0d8","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"jpeg","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":425283,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage27.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/a1038d168ca2a51e9b2c78cd.jpeg"},{"id":97250423,"identity":"93158582-6a78-4342-9a08-a8d01aec57fa","added_by":"auto","created_at":"2025-12-02 13:14:29","extension":"jpeg","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":221862,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage28.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/d8ee0cb6f56be55b744b8df7.jpeg"},{"id":97250193,"identity":"dd2f940f-dfe9-4d53-8b6d-b5ed509bf47a","added_by":"auto","created_at":"2025-12-02 13:14:04","extension":"jpeg","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1311,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/ac7e4f36598795e43cf3d088.jpeg"},{"id":97250092,"identity":"924345c5-cb55-45b5-8f3d-4932d11a82e2","added_by":"auto","created_at":"2025-12-02 13:13:54","extension":"jpeg","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":300712,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/9eeb6bed23284d31205870af.jpeg"},{"id":97229265,"identity":"7465c41a-13ad-4f0e-bc3d-2447953f3171","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"jpeg","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":130568,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/e44d6c5a999cf8f35f25007d.jpeg"},{"id":97251034,"identity":"f44c686e-ff57-41db-85b0-53fe6ad5fe9c","added_by":"auto","created_at":"2025-12-02 13:15:50","extension":"jpeg","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":103211,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/73d11c53199765767aba6d72.jpeg"},{"id":97251255,"identity":"2767753b-cbc4-4aed-ad31-96479dddf1f2","added_by":"auto","created_at":"2025-12-02 13:16:35","extension":"jpeg","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":168288,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/63ea56c43399c32162259b89.jpeg"},{"id":97229279,"identity":"2da3d653-8ed2-4381-a3b4-6670a6c0b38f","added_by":"auto","created_at":"2025-12-02 09:02:44","extension":"jpeg","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":147090,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/bfcc202575e375aef3da1939.jpeg"},{"id":97250628,"identity":"516d1005-9888-40aa-835e-876da7f6872a","added_by":"auto","created_at":"2025-12-02 13:14:50","extension":"jpeg","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1074,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage18.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/6efbd25312f66858c37b6f1b.jpeg"},{"id":97229282,"identity":"1a26a220-20e8-467c-8753-4985ddf9d4b7","added_by":"auto","created_at":"2025-12-02 09:02:44","extension":"jpeg","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24719,"visible":true,"origin":"","legend":"","description":"","filename":"groupimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/b8fe1d855091dccebb668fca.jpeg"},{"id":97229267,"identity":"98dbceb5-398b-41ce-af11-7509e9336333","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"jpeg","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16967,"visible":true,"origin":"","legend":"","description":"","filename":"groupimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/3aced4e427f96e0d4afaba2b.jpeg"},{"id":97251119,"identity":"2f9830c4-0f4c-4dd8-955f-3a53557a7aa8","added_by":"auto","created_at":"2025-12-02 13:16:06","extension":"png","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":956,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/4bb13b332b0de03c2f46bcf6.png"},{"id":97229261,"identity":"3ae4f2b9-b3ac-4c58-a2fc-55f8ab9b4114","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"png","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":59133,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/24b46a331421a34faaf3b4fb.png"},{"id":97250957,"identity":"65ba4341-f162-425e-8b7e-9d0ea3ac6bc2","added_by":"auto","created_at":"2025-12-02 13:15:40","extension":"png","order_by":40,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16134,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/e4539d582a3b12759e44d042.png"},{"id":97229275,"identity":"d5d8ac92-f363-4f29-8426-8434d56e08c8","added_by":"auto","created_at":"2025-12-02 09:02:44","extension":"png","order_by":41,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6489,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/c9416c1fa0c4503594f1e79c.png"},{"id":97229271,"identity":"cdb0cce3-55d1-4672-a0a9-17ccf2eeb452","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"png","order_by":42,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12617,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/956900b957a1f75e4177f376.png"},{"id":97250110,"identity":"d4c27529-eb81-4699-a80e-95fd3a8ab483","added_by":"auto","created_at":"2025-12-02 13:13:55","extension":"png","order_by":43,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40910,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/09af0c883ecd343a5d8daa46.png"},{"id":97229274,"identity":"0bc7d9de-e800-425d-a87c-164ce2b1bc70","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"png","order_by":44,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1923,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/750831fe40ddb7bf81b58cfd.png"},{"id":97229270,"identity":"f062696e-1068-4a6d-bd13-18445c90b69c","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"png","order_by":45,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32477,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage16.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/e793134fd482b1d86521f353.png"},{"id":97229303,"identity":"366e86c5-a1ca-48ae-af1b-7b5c13994957","added_by":"auto","created_at":"2025-12-02 09:02:44","extension":"png","order_by":46,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":109286,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage17.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/2a24397e56147b55577496fe.png"},{"id":97229268,"identity":"4cf8699a-3131-495d-bcfb-bdaf13526a8e","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"png","order_by":47,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":935,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage18.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/36d1bd0ddaaa17373705dcc6.png"},{"id":97229273,"identity":"782b8e5a-104c-4015-bd57-691063c8b7fc","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"png","order_by":48,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41366,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage19.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/e31743ae73128074d5beb93a.png"},{"id":97229272,"identity":"b284bc52-6f03-4853-9c33-147590aac056","added_by":"auto","created_at":"2025-12-02 09:02:43","extension":"png","order_by":49,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":935,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage18.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/125d1fd4eb420f320959fdb7.png"},{"id":97250244,"identity":"a069b9b0-9149-4bbb-a039-1b1faac86ed4","added_by":"auto","created_at":"2025-12-02 13:14:10","extension":"png","order_by":50,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":935,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage18.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/6544f40782c14b48fd8c12ae.png"},{"id":97229286,"identity":"398941d9-909a-4591-a57c-91550a9035f4","added_by":"auto","created_at":"2025-12-02 09:02:44","extension":"png","order_by":51,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39724,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage21.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/22daf9ab75c23f86f39d4901.png"},{"id":97229293,"identity":"de595315-1e41-4d25-9749-fd534cda0cdd","added_by":"auto","created_at":"2025-12-02 09:02:44","extension":"png","order_by":52,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13777,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage22.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/bd07fa95d806fca0f051647c.png"},{"id":97251085,"identity":"e1c5b1ef-2981-4dd6-9a05-aaa0bdee5042","added_by":"auto","created_at":"2025-12-02 13:16:00","extension":"png","order_by":53,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20105,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage23.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/242202808bce13670e0d3375.png"},{"id":97250530,"identity":"10c00ada-91aa-41b2-bf20-c6594170d9c3","added_by":"auto","created_at":"2025-12-02 13:14:39","extension":"png","order_by":54,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14966,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage24.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/d7a76de1531348f57b3d9246.png"},{"id":97250234,"identity":"81a56c9c-8eed-4ee4-a695-cbacea79f44d","added_by":"auto","created_at":"2025-12-02 13:14:09","extension":"png","order_by":55,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":362,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage25.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/de53f7e6df6b14924cd718a6.png"},{"id":97251057,"identity":"e44725c6-fa00-4eb4-b6aa-a906d9c62c94","added_by":"auto","created_at":"2025-12-02 13:15:54","extension":"png","order_by":56,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9642,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage26.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/55c1acfa6e7ad94711e60d90.png"},{"id":97250278,"identity":"4b16dd5d-f98d-4e72-ae48-5658d13c0fa4","added_by":"auto","created_at":"2025-12-02 13:14:12","extension":"png","order_by":57,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":78772,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage27.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/db01c294b68433d251f37603.png"},{"id":97251234,"identity":"9d202eda-4230-4ae3-af2f-2535d9455f34","added_by":"auto","created_at":"2025-12-02 13:16:28","extension":"png","order_by":58,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":44752,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage28.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/6aafb94f752c7144e74e1eff.png"},{"id":97229300,"identity":"09e862a3-a289-415f-ace8-c5463ae0ab64","added_by":"auto","created_at":"2025-12-02 09:02:44","extension":"png","order_by":59,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":949,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/26defca57262d517b126ea81.png"},{"id":97250330,"identity":"6ced00cf-bfb7-4898-b5c6-897492e97e4d","added_by":"auto","created_at":"2025-12-02 13:14:16","extension":"png","order_by":60,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":79329,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/41ac64f463917931d2452076.png"},{"id":97251095,"identity":"f32aed4f-4901-49ef-948d-7aabf0c9ab4e","added_by":"auto","created_at":"2025-12-02 13:16:02","extension":"png","order_by":61,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":34837,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/04f2be2254ddcd347d6d9a20.png"},{"id":97251144,"identity":"4a2d1e5a-6467-46f2-9d3d-e29198dba15f","added_by":"auto","created_at":"2025-12-02 13:16:13","extension":"png","order_by":62,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20312,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/f9f724ef551de295c7bb2a1f.png"},{"id":97229301,"identity":"2e0c8d28-b8c0-4684-99db-d4f5cfa0365e","added_by":"auto","created_at":"2025-12-02 09:02:44","extension":"png","order_by":63,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":34822,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/d749a9b41636b3c39f858096.png"},{"id":97229281,"identity":"c8023ade-1f4c-45ba-9e91-e44f3f5b14ce","added_by":"auto","created_at":"2025-12-02 09:02:44","extension":"png","order_by":64,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28632,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/7a5800d8b7b04d0173ef9156.png"},{"id":97250039,"identity":"91afd54f-4a57-4ead-ba89-d218951734c9","added_by":"auto","created_at":"2025-12-02 13:13:49","extension":"png","order_by":65,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":935,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage18.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/2fd34f791cd0aad39e7d9f3a.png"},{"id":97229284,"identity":"5a4d06d3-f00d-4abf-beb0-8fefb64b028d","added_by":"auto","created_at":"2025-12-02 09:02:44","extension":"png","order_by":66,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14368,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinegroupimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/cf9d704ff1d452a81ff15d9c.png"},{"id":97250939,"identity":"8de21249-6f82-4aa2-9a1c-b5b2dcbe9c7f","added_by":"auto","created_at":"2025-12-02 13:15:38","extension":"png","order_by":67,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9885,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinegroupimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/5b4380795269d0c18963377c.png"},{"id":97250252,"identity":"bdbc1444-41b4-4748-8132-78d330a10f44","added_by":"auto","created_at":"2025-12-02 13:14:10","extension":"xml","order_by":68,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":110211,"visible":true,"origin":"","legend":"","description":"","filename":"6d75a00905204fceb244566cf3ba90a71structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/c6f560126c93f56da6f67e33.xml"},{"id":97251163,"identity":"bc6c2ba2-df89-4a71-ab4b-50d9260874a2","added_by":"auto","created_at":"2025-12-02 13:16:16","extension":"html","order_by":69,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124907,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1/403b37f52e574414eec260b1.html"},{"id":97369345,"identity":"9012ab19-34e7-42c0-b12d-dd69a6cb997a","added_by":"auto","created_at":"2025-12-03 16:24:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":718972,"visible":true,"origin":"","legend":"","description":"","filename":"drafdmkd.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8236211/v1_covered_db3c9ff5-a8bd-4fa7-ab82-b1816eb3bbf9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"The Decline of Synthetic Oversampling in Large-Scale Imbalanced Learning:A Post-SMOTE Empirical and Theoretical Study (2020–2025)","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":"Class imbalance, SMOTE, Diffusion models, Cost-sensitive learning, Systematic review","lastPublishedDoi":"10.21203/rs.3.rs-8236211/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8236211/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFor over twenty years, SMOTE has been the standard default for addressing class imbalance. Yet a striking paradox has emerged: while researchers continue citing SMOTE extensively, practitioners have largely abandoned it in production systems. To understand this disconnect, we conducted a large-scale empirical and theoretical study of \u003cb\u003e821 papers\u003c/b\u003e published between 2020\u0026ndash;2025, revealing a fundamental paradigm shift. Approximately \u003cb\u003e30%\u003c/b\u003e of new solutions now employ Generative AI (Diffusion Models), \u003cb\u003e30%\u003c/b\u003e rely on cost-sensitive loss functions, while the remainder explore hybrid approaches. We mathematically show why SMOTE fails at modern scales: its \u003cem\u003eO\u003c/em\u003e(\u003cem\u003eN\u003c/em\u003e \u003csup\u003e2\u003c/sup\u003e) complexity exhausts memory on billion-sample datasets, its nearest-neighbor logic distorts high-dimensional manifolds, and its CPU-bound design is incompatible with GPU pipelines. Beyond theory, we identify the novel \u0026ldquo;SMOTE Paradox\u0026rdquo;\u0026mdash;the critical divergence between academic citations and real-world deployment. This systematic study maps the emerging post-SMOTE landscape, syn- thesizes theoretical foundations across three competing paradigms, and provides decision rules for practitioners. Empirically, we validate these findings on real-world fraud data (N\u0026thinsp;=\u0026thinsp;284,807, im- balance 578:1), confirming that cost-sensitive learning achieves parity with oversampling (+\u0026thinsp;0.29% F1-score improvement) while eliminating preprocessing overhead. Our contributions include: (1) quantitative documentation of the paradigm shift through systematic analysis, (2) mathematical proofs of SMOTE\u0026rsquo;s failure modes, (3) the novel SMOTE Paradox framework, and (4) empirical validation on production-scale data. We conclude with actionable guidelines for practitioners and identify two critical open problems for future research in large-scale imbalanced learning.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e","manuscriptTitle":"The Decline of Synthetic Oversampling in Large-Scale Imbalanced Learning:A Post-SMOTE Empirical and Theoretical Study (2020–2025)","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-02 09:02:38","doi":"10.21203/rs.3.rs-8236211/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":"c1716045-ed0f-44c0-a5b1-4f04c3f7c802","owner":[],"postedDate":"December 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-03T06:39:06+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-02 09:02:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8236211","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8236211","identity":"rs-8236211","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00