TriBal: An Ensemble Learning Three-Level Data Balancing Framework for Click Fraud Detection in Online Advertising

TriBal: An Ensemble Learning Three-Level Data Balancing Framework for Click Fraud Detection in Online Advertising | 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 Article TriBal: An Ensemble Learning Three-Level Data Balancing Framework for Click Fraud Detection in Online Advertising Deepti Sisodia, Lokesh Singh This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8007463/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 Click fraud in online advertising, where malicious actors generate fake clicks, presents a significant challenge due to the class imbalance between legitimate and fraudulent clicks. This study proposes 'TriBal', an ensemble resampling framework designed to detect click fraud by employing a three-level data balancing approach using SMOTE, Cluster Centroids, and Edited Nearest Neighbors (ENN). At Level 1, SMOTE is applied to oversample the minority class (fraudulent clicks), generating synthetic data to ensure the classifier has sufficient information to learn fraud patterns. Level 2 uses Cluster Centroids to under-sample the majority class (legitimate clicks) by condensing them into representative samples, reducing redundancy and further balancing the dataset. ENN is employed at Level 3, to remove noisy and misclassified instances near the decision boundary which results in an ensemble balance dataset, which is further refined by eliminating confusing data points. The effectiveness of TriBal is evaluated on nine benchmark datasets using 10-fold cross-validation, with performance measured through average precision, recall, and F1-score. Experimental results demonstrate that the proposed methodology is a more efficient alternative to existing sampling techniques, offering improved performance in detecting click fraud. Physical sciences/Engineering Physical sciences/Mathematics and computing online advertising click fraud class imbalance data sampling techniques multi-level sampling 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-8007463","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":549349626,"identity":"72d9252c-65cf-4d7a-b3f8-46cfe95957dd","order_by":0,"name":"Deepti Sisodia","email":"","orcid":"","institution":"manipal institute of technology bengaluru","correspondingAuthor":false,"prefix":"","firstName":"Deepti","middleName":"","lastName":"Sisodia","suffix":""},{"id":549349627,"identity":"a60d5539-b5d6-4790-a9db-79accb207c6e","order_by":1,"name":"Lokesh Singh","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFElEQVRIie3RwUrDMBjA8a8Eeoo7f6VzfYVAoCpVn6VFsJdOBl4GCg4G7UXxOhjoM3jJORBYL32IwaAevBQ87SKm3YR5SM+C+RMCCfmRQABstr8Y6cYpIIALDbQzOLLb7CfYEWexI9BP4IAQut/pJUFxpD4mgCOvKOrNRXZ5M/DnawnTKJkZCFOD62gByH1anfCxuLp1hysmoUrNhNCQU8DkBTPXHwuS5Bgz6eTKSIL5Dwnea/9MPGiSNtL5MhNQlG9askQIfUcoTTJ9y8xMmKIhoQy595iF3pMok3xYTWS8SrnxYc8V/6TT8xGWZY1bcZe8Lou3dXMfHRsfpr8DgR2u9Q9BbD7eRprfa+w/brPZbP+vbzZdUQ+Q8DoqAAAAAElFTkSuQmCC","orcid":"","institution":"manipal institute of technology bengaluru","correspondingAuthor":true,"prefix":"","firstName":"Lokesh","middleName":"","lastName":"Singh","suffix":""}],"badges":[],"createdAt":"2025-11-01 18:38:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8007463/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8007463/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96937551,"identity":"df4cb855-2ec2-450f-9737-b1f2569f2da1","added_by":"auto","created_at":"2025-11-27 16:59:06","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1028692,"visible":true,"origin":"","legend":"","description":"","filename":"TRIBALManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007463/v1/cd7f2d46ab10db575de93c6c.pdf"},{"id":96937550,"identity":"402e0ae1-4dfb-4894-8b72-0262c32e3874","added_by":"auto","created_at":"2025-11-27 16:59:06","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4411,"visible":true,"origin":"","legend":"","description":"","filename":"328b1361c04a46f2aa9d0ce9f7324b1c.json","url":"https://assets-eu.researchsquare.com/files/rs-8007463/v1/8af8696cd2f9008c50c3bc42.json"},{"id":103301439,"identity":"88910521-06ac-4f27-835e-89c0304732f9","added_by":"auto","created_at":"2026-02-24 08:12:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":978311,"visible":true,"origin":"","legend":"","description":"","filename":"TRIBALManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007463/v1_covered_4a66f619-a6e7-471d-bf50-e4e47881b245.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"TriBal: An Ensemble Learning Three-Level Data Balancing Framework for Click Fraud Detection in Online Advertising","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":"online advertising, click fraud, class imbalance, data sampling techniques, multi-level sampling","lastPublishedDoi":"10.21203/rs.3.rs-8007463/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8007463/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Click fraud in online advertising, where malicious actors generate fake clicks, presents a significant challenge due to the class imbalance between legitimate and fraudulent clicks. This study proposes 'TriBal', an ensemble resampling framework designed to detect click fraud by employing a three-level data balancing approach using SMOTE, Cluster Centroids, and Edited Nearest Neighbors (ENN). At Level 1, SMOTE is applied to oversample the minority class (fraudulent clicks), generating synthetic data to ensure the classifier has sufficient information to learn fraud patterns. Level 2 uses Cluster Centroids to under-sample the majority class (legitimate clicks) by condensing them into representative samples, reducing redundancy and further balancing the dataset. ENN is employed at Level 3, to remove noisy and misclassified instances near the decision boundary which results in an ensemble balance dataset, which is further refined by eliminating confusing data points. The effectiveness of TriBal is evaluated on nine benchmark datasets using 10-fold cross-validation, with performance measured through average precision, recall, and F1-score. Experimental results demonstrate that the proposed methodology is a more efficient alternative to existing sampling techniques, offering improved performance in detecting click fraud.","manuscriptTitle":"TriBal: An Ensemble Learning Three-Level Data Balancing Framework for Click Fraud Detection in Online Advertising","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-27 16:59:01","doi":"10.21203/rs.3.rs-8007463/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":"a15cffc4-651a-4263-bb29-cd1e1cd42c2d","owner":[],"postedDate":"November 27th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":58452466,"name":"Physical sciences/Engineering"},{"id":58452467,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-02-24T08:11:21+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-27 16:59:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8007463","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8007463","identity":"rs-8007463","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}