SOD-FE: A Supervised Outlier Detection and Feature Engineering Approach for Student Dropout Prediction

SOD-FE: A Supervised Outlier Detection and Feature Engineering Approach for Student Dropout Prediction | 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 SOD-FE: A Supervised Outlier Detection and Feature Engineering Approach for Student Dropout Prediction Sabah Saad, Önder Yakut, Eissa Alzabidi, Oğuz Fındık This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6889300/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract Student dropout in higher education creates academic and socioeconomic challenges for institutions and students. Effective early prediction models are essential to identify at-risk students and implement timely interventions. This paper proposes SOD-FE, a supervised machine learning approach that combines label-aware outlier detection with feature engineering to enhance dropout prediction. The approach integrates interquartile range (IQR) based outlier detection with mutual information and Pearson correlation to identify and mitigate the impact of outliers before constructing the final model. Then, a feature selection strategy is applied to refine the dataset. The approach is evaluated through experiments on two real-world datasets (Portugal and Slovakia) utilizing five classification algorithms, including Random Forest (RF) and Extreme Gradient Boosting (XGB). Performance increased greatly with the RF classifier, achieving F1 scores of 98.09% and 98.33% on two benchmark datasets, using 5-fold cross-validation. The proposed approach also incorporates explainable AI techniques (SHAP) to enhance model transparency and support data-driven educational policy. These findings show the significant potential of the SOD-FE method for improving student retention and early intervention systems in educational institutions. Physical sciences/Mathematics and computing/Applied mathematics Physical sciences/Mathematics and computing/Computational science Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology Physical sciences/Mathematics and computing/Statistics Student Dropout Prediction Supervised Outlier Detection Feature Engineering Machine Learning XAI Full Text Additional Declarations No competing interests reported. Supplementary Files LaTeXwithfunding.zip Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 23 Mar, 2026 Reviews received at journal 26 Jan, 2026 Reviews received at journal 24 Jan, 2026 Reviewers agreed at journal 24 Jan, 2026 Reviewers agreed at journal 24 Jan, 2026 Reviewers agreed at journal 23 Jan, 2026 Reviewers agreed at journal 20 Oct, 2025 Reviewers agreed at journal 17 Oct, 2025 Reviewers invited by journal 17 Oct, 2025 Editor invited by journal 17 Jun, 2025 Editor assigned by journal 16 Jun, 2025 Submission checks completed at journal 16 Jun, 2025 First submitted to journal 13 Jun, 2025 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-6889300","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":473589463,"identity":"447ebddc-c602-47f1-bb0a-2fa2ddd430fa","order_by":0,"name":"Sabah Saad","email":"","orcid":"","institution":"Kocaeli University","correspondingAuthor":false,"prefix":"","firstName":"Sabah","middleName":"","lastName":"Saad","suffix":""},{"id":473589464,"identity":"ae6c1612-0ec1-4449-9463-f8b0a01682e0","order_by":1,"name":"Önder Yakut","email":"","orcid":"","institution":"Kocaeli University","correspondingAuthor":false,"prefix":"","firstName":"Önder","middleName":"","lastName":"Yakut","suffix":""},{"id":473589465,"identity":"112d3955-1ed2-4d53-b823-c278be6ecfd8","order_by":2,"name":"Eissa Alzabidi","email":"data:image/png;base64,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","orcid":"","institution":"Hodeidah University","correspondingAuthor":true,"prefix":"","firstName":"Eissa","middleName":"","lastName":"Alzabidi","suffix":""},{"id":473589466,"identity":"5822c1bc-cb2f-4af3-a99a-ddfbd0af5b61","order_by":3,"name":"Oğuz Fındık","email":"","orcid":"","institution":"Karabük University","correspondingAuthor":false,"prefix":"","firstName":"Oğuz","middleName":"","lastName":"Fındık","suffix":""}],"badges":[],"createdAt":"2025-06-13 15:08:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6889300/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6889300/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":85012999,"identity":"b3097b5a-e197-4474-ab03-116c99b0f723","added_by":"auto","created_at":"2025-06-20 02:17:55","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":942859,"visible":true,"origin":"","legend":"","description":"","filename":"manuscriptwithfunding.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6889300/v1_covered_b3430d15-8bfd-41e0-a0f8-d50fdc7ff473.pdf"},{"id":85012885,"identity":"442f815e-e47c-41b7-a6d8-9a47926f5d5f","added_by":"auto","created_at":"2025-06-20 02:09:54","extension":"zip","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":3455651,"visible":true,"origin":"","legend":"","description":"","filename":"LaTeXwithfunding.zip","url":"https://assets-eu.researchsquare.com/files/rs-6889300/v1/823b7f14a70c84ae88497f6a.zip"}],"financialInterests":"No competing interests reported.","formattedTitle":"SOD-FE: A Supervised Outlier Detection and Feature Engineering Approach for Student Dropout Prediction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Student Dropout Prediction, Supervised Outlier Detection, Feature Engineering, Machine Learning, XAI","lastPublishedDoi":"10.21203/rs.3.rs-6889300/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6889300/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Student dropout in higher education creates academic and socioeconomic challenges for institutions and students. Effective early prediction models are essential to identify at-risk students and implement timely interventions. This paper proposes SOD-FE, a supervised machine learning approach that combines label-aware outlier detection with feature engineering to enhance dropout prediction. The approach integrates interquartile range (IQR) based outlier detection with mutual information and Pearson correlation to identify and mitigate the impact of outliers before constructing the final model. Then, a feature selection strategy is applied to refine the dataset. The approach is evaluated through experiments on two real-world datasets (Portugal and Slovakia) utilizing five classification algorithms, including Random Forest (RF) and Extreme Gradient Boosting (XGB). Performance increased greatly with the RF classifier, achieving F1 scores of 98.09% and 98.33% on two benchmark datasets, using 5-fold cross-validation. The proposed approach also incorporates explainable AI techniques (SHAP) to enhance model transparency and support data-driven educational policy. These findings show the significant potential of the SOD-FE method for improving student retention and early intervention systems in educational institutions.","manuscriptTitle":"SOD-FE: A Supervised Outlier Detection and Feature Engineering Approach for Student Dropout Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-20 02:09:48","doi":"10.21203/rs.3.rs-6889300/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-23T11:08:46+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-26T11:21:29+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-24T16:39:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"73654851669661628589676612442712744662","date":"2026-01-24T16:37:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"32764971784672377075119908853979873853","date":"2026-01-24T08:51:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"247286770313811847761605447306524876989","date":"2026-01-23T08:47:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"86057451028263613095440089600106456947","date":"2025-10-20T08:23:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"150936282222973185390485237294603853727","date":"2025-10-18T01:33:36+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-17T17:46:59+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-06-17T10:11:15+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-16T12:34:32+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-16T08:51:09+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-06-13T14:54:06+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ea6ef202-cf4c-487a-b5e4-df5fe4a18c36","owner":[],"postedDate":"June 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":50295276,"name":"Physical sciences/Mathematics and computing/Applied mathematics"},{"id":50295277,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":50295278,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":50295279,"name":"Physical sciences/Mathematics and computing/Information technology"},{"id":50295280,"name":"Physical sciences/Mathematics and computing/Statistics"}],"tags":[],"updatedAt":"2026-04-07T15:08:51+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-20 02:09:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6889300","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6889300","identity":"rs-6889300","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}