Fairness and Bias Mitigation in Student Success Prediction Models

Fairness and Bias Mitigation in Student Success Prediction Models | 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 Fairness and Bias Mitigation in Student Success Prediction Models Godfrey Perfectson Oise This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7899983/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 The adoption of machine learning (ML) and artificial intelligence (AI) in higher education has revolutionized student success prediction by enabling institutions to forecast academic outcomes, identify at-risk learners, and provide timely interventions. Yet, these predictive systems often inherit historical and structural inequities present in educational data, leading to algorithmic bias and unfair treatment of marginalized student groups. This study proposes a fairness-aware predictive framework that integrates bias detection, mitigation, and interpretability into all stages of the modeling process. Using a real-world Student Performance & Behavior Dataset containing 5,000 student records, five ML algorithms, Random Forest, Gradient Boosting, Support Vector Machine, K-Nearest Neighbors, and Logistic Regression were evaluated based on accuracy, precision, recall, and F1-score, alongside fairness metrics to assess equity performance. The Random Forest model achieved the highest predictive accuracy (37%), but fairness analysis revealed class imbalance and unequal group representation. To address these disparities, the proposed framework emphasizes three guiding principles: Fairness by Design, incorporating fairness constraints during data preprocessing and model training; Ethical Transparency, employing explainable AI tools to ensure accountability and stakeholder understanding; and Sociotechnical Alignment, embedding algorithmic decisions within institutional equity policies. The results highlight the importance of harmonizing predictive performance with fairness and ethical accountability. Ultimately, this work advances the field of responsible learning analytics by demonstrating that bias-aware predictive modeling can transform student success systems from efficiency-driven mechanisms into equitable, transparent, and socially responsible tools that foster educational justice and inclusion. fairness-aware learning bias mitigation learning analytics predictive modeling student retention counterfactual fairness ethical AI education data mining 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-7899983","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":542051302,"identity":"96f0247a-0cfb-4125-931b-fcb66faeadbc","order_by":0,"name":"Godfrey Perfectson Oise","email":"data:image/png;base64,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","orcid":"","institution":"University of Benin","correspondingAuthor":true,"prefix":"","firstName":"Godfrey","middleName":"Perfectson","lastName":"Oise","suffix":""}],"badges":[],"createdAt":"2025-10-19 17:08:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7899983/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7899983/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95831277,"identity":"31ea4e16-4c26-4fa0-850a-7d00e6bc3d54","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":919904,"visible":true,"origin":"","legend":"","description":"","filename":"FairnessandBiasMitigationinStudentSuccessPredictionModels.docx","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/3d34abf673060c686399fd7f.docx"},{"id":95831267,"identity":"251f7885-aa01-4863-94e8-609447a365af","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4087,"visible":true,"origin":"","legend":"","description":"","filename":"6d4d6e0addf545539bda67551052d6cb.json","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/16bb6f62f9ba6d0dfd4d5b67.json"},{"id":95831269,"identity":"c356eb41-ac14-4dcd-a23f-778fb80f3473","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":126602,"visible":true,"origin":"","legend":"","description":"","filename":"6d4d6e0addf545539bda67551052d6cb1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/e6478bee5a832cb7236c1237.xml"},{"id":95831278,"identity":"e393705c-d106-45ab-921a-e2071bf85f81","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":133582,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/023592e5bfb2fb76b0729a1e.png"},{"id":95831268,"identity":"7602d178-b8a5-40ce-a3e7-eaf2d3ab290b","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15007,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/3a28233ea416655138ee9409.png"},{"id":95831279,"identity":"8a05882e-d983-4f23-84b4-f9e7a92d8544","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":118695,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/5dc500e025636b367e60dd6b.png"},{"id":95831274,"identity":"21f486c5-fde6-4c91-b5b9-6a62f3d65071","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":265365,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/db645ce0e1848a16061adc07.png"},{"id":96239597,"identity":"63bfd037-cab2-4f3d-b8bd-78f15b23b881","added_by":"auto","created_at":"2025-11-19 07:07:06","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19282,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/a704e0c51097087f94b380e6.png"},{"id":96240972,"identity":"718f9324-d86a-4def-a794-525690affeb7","added_by":"auto","created_at":"2025-11-19 07:09:47","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":114862,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/506ab12b5324916cbf19fcc3.png"},{"id":95831272,"identity":"5784f315-d414-405b-83ed-b43599299b2e","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19850,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/6c3fcd356a17f782c37a4241.png"},{"id":96239479,"identity":"85f89684-e75f-48be-b8a7-da9d9dc83fce","added_by":"auto","created_at":"2025-11-19 07:06:45","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36480,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/be00162dfa6acec8fd89aa98.png"},{"id":95831270,"identity":"0e502555-d6e0-4e80-bb8e-a05f717af39d","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":44318,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/70be3d771fc33aeb34da0af7.png"},{"id":96239748,"identity":"d5188505-c39d-4c9e-93e5-7d9ef1423e7e","added_by":"auto","created_at":"2025-11-19 07:07:32","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":38284,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/4af57197b9cb6147020438ee.png"},{"id":95831285,"identity":"9e4ab259-b4ab-4f48-8c64-1d5fdb0e4381","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4377,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/28c9cdae167f486fe8dcbaba.png"},{"id":96239458,"identity":"ce12ee8b-686f-4a26-98e4-07bd038a8c30","added_by":"auto","created_at":"2025-11-19 07:06:44","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32509,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/1b9b66af4b7905477c081bad.png"},{"id":95831281,"identity":"a0df7aca-64f3-4200-8d87-1c544eede516","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":70446,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/c197662fa8c9f2f9074a481b.png"},{"id":95831282,"identity":"d4fc2909-8de8-4966-bf1b-fa8a20d3ff37","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6207,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/a9d197ad2980cddaad2792d5.png"},{"id":96239565,"identity":"efe5b330-2bc9-4877-b3c8-8fbed2ee94e3","added_by":"auto","created_at":"2025-11-19 07:06:59","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":50122,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/b864f3f141a5b4bbaf1079e1.png"},{"id":96239799,"identity":"e09d848e-cc17-48b4-8773-7ca799e2f1c5","added_by":"auto","created_at":"2025-11-19 07:07:43","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6404,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/53bc32827fa010a2e5552ab1.png"},{"id":95831283,"identity":"415cbc09-a125-4631-8d26-d538edb30ca0","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10796,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/0ad078864414806d3e16b48d.png"},{"id":95831287,"identity":"79ddb7bb-e557-4633-884c-09b2d3da540b","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13460,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/0c240f5fcd306b4072b81f9d.png"},{"id":95831289,"identity":"a091c002-4d8d-4d74-9133-bad6cf35d047","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"xml","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124702,"visible":true,"origin":"","legend":"","description":"","filename":"6d4d6e0addf545539bda67551052d6cb1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/efd1bbf88932b54e309d690a.xml"},{"id":95831288,"identity":"145b860c-e957-4587-842e-172992a4fd89","added_by":"auto","created_at":"2025-11-13 12:27:33","extension":"html","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":136897,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1/253d282a2cb04c1aa31bee7e.html"},{"id":100607076,"identity":"65ae7c9d-41cc-400d-b15d-2f978822971d","added_by":"auto","created_at":"2026-01-19 15:59:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":837778,"visible":true,"origin":"","legend":"","description":"","filename":"FairnessandBiasMitigationinStudentSuccessPredictionModels.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7899983/v1_covered_0acaf4fc-05b5-4a54-9bdc-6a7922fc82af.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Fairness and Bias Mitigation in Student Success Prediction Models","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":"fairness-aware learning, bias mitigation, learning analytics, predictive modeling, student retention, counterfactual fairness, ethical AI, education data mining","lastPublishedDoi":"10.21203/rs.3.rs-7899983/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7899983/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe adoption of machine learning (ML) and artificial intelligence (AI) in higher education has revolutionized student success prediction by enabling institutions to forecast academic outcomes, identify at-risk learners, and provide timely interventions. Yet, these predictive systems often inherit historical and structural inequities present in educational data, leading to algorithmic bias and unfair treatment of marginalized student groups. This study proposes a fairness-aware predictive framework that integrates bias detection, mitigation, and interpretability into all stages of the modeling process. Using a real-world Student Performance \u0026amp; Behavior Dataset containing 5,000 student records, five ML algorithms, Random Forest, Gradient Boosting, Support Vector Machine, K-Nearest Neighbors, and Logistic Regression were evaluated based on accuracy, precision, recall, and F1-score, alongside fairness metrics to assess equity performance. The Random Forest model achieved the highest predictive accuracy (37%), but fairness analysis revealed class imbalance and unequal group representation. To address these disparities, the proposed framework emphasizes three guiding principles: Fairness by Design, incorporating fairness constraints during data preprocessing and model training; Ethical Transparency, employing explainable AI tools to ensure accountability and stakeholder understanding; and Sociotechnical Alignment, embedding algorithmic decisions within institutional equity policies. The results highlight the importance of harmonizing predictive performance with fairness and ethical accountability. Ultimately, this work advances the field of responsible learning analytics by demonstrating that bias-aware predictive modeling can transform student success systems from efficiency-driven mechanisms into equitable, transparent, and socially responsible tools that foster educational justice and inclusion.\u003c/p\u003e","manuscriptTitle":"Fairness and Bias Mitigation in Student Success Prediction Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-13 12:27:28","doi":"10.21203/rs.3.rs-7899983/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":"750b9206-1b8a-47b3-b3ab-df823c68ecee","owner":[],"postedDate":"November 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-19T14:54:20+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-13 12:27:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7899983","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7899983","identity":"rs-7899983","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}