Predicting Learning Achievement Using Ensemble Learning with Result Explanation

Predicting Learning Achievement Using Ensemble Learning with Result Explanation | 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 Predicting Learning Achievement Using Ensemble Learning with Result Explanation Tingting Tong, Zhen Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4674228/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 Predicting learning achievement is a crucial strategy to address high dropout rates. However, existing prediction models often exhibit biases, limiting their accuracy. Moreover, the lack of interpretability in current machine learning methods restricts their practical application in education. To overcome these challenges, this research combines the strengths of various machine learning algorithms to design a robust model that performs well across multiple metrics, and uses interpretability analysis to elucidate the prediction results. This study introduces a predictive framework for learning achievement based on ensemble learning techniques. Specifically, six distinct machine learning models are utilized to establish a base learner, with logistic regression serving as the meta-learner to construct an ensemble model for predicting academic performance. The SHapley Additive exPlanation (SHAP) model is then employed to explain the prediction results. The model’s accuracy was validated on classification tasks. The results demonstrate that the ensemble learning-based predictive framework significantly outperforms conventional machine learning methods. Through feature importance analysis, the SHAP method enhances model interpretability and improves the reliability of the prediction results, enabling more personalized interventions to support students. Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology 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-4674228","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":331682996,"identity":"29a38dbc-a028-4f74-aba5-411d8305f954","order_by":0,"name":"Tingting Tong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5klEQVRIiWNgGAWjYPACGx5+9gYo+wABtTxgRQlpMpI9MKVEajlkYzAjgUgt9uy9h19//HGAx0Dy7cHHhW0Mcnw3Ehg/F+CzhedcmsWBhDs85tJ5ycYz2xiMJW8kMEvPwKdFIsfM4EDCMx7L2Tlm0rxtDIkbbiSwMfMQ1nKYx+DmGfPfQC31xGgxfgDWcoPHjBmoJcGAoJYzZ8wYzqSl8Uj25BhL85yTMJx55mGzND4t7O09xh8qbGzs+dnPGH7mKbOR5zuefPAzPi1AwCaBxAGxGRvwa2BgYP5ASMUoGAWjYBSMcAAAkZlJQ/oWl1AAAAAASUVORK5CYII=","orcid":"","institution":"Northeast Normal University","correspondingAuthor":true,"prefix":"","firstName":"Tingting","middleName":"","lastName":"Tong","suffix":""},{"id":331682997,"identity":"80dd1e36-5c15-49ca-bb35-75205c0e0cf6","order_by":1,"name":"Zhen Li","email":"","orcid":"","institution":"Northeast Normal University","correspondingAuthor":false,"prefix":"","firstName":"Zhen","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2024-07-02 12:31:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4674228/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4674228/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":62029218,"identity":"44a477c5-17a3-493b-b60d-6aba445e3de9","added_by":"auto","created_at":"2024-08-08 11:52:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":437605,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4674228/v1_covered_25caf1b7-ec99-4fa2-894c-69efbed25290.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Predicting Learning Achievement Using Ensemble Learning with Result Explanation","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":"","lastPublishedDoi":"10.21203/rs.3.rs-4674228/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4674228/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Predicting learning achievement is a crucial strategy to address high dropout rates. However, existing prediction models often exhibit biases, limiting their accuracy. Moreover, the lack of interpretability in current machine learning methods restricts their practical application in education. To overcome these challenges, this research combines the strengths of various machine learning algorithms to design a robust model that performs well across multiple metrics, and uses interpretability analysis to elucidate the prediction results. This study introduces a predictive framework for learning achievement based on ensemble learning techniques. Specifically, six distinct machine learning models are utilized to establish a base learner, with logistic regression serving as the meta-learner to construct an ensemble model for predicting academic performance. The SHapley Additive exPlanation (SHAP) model is then employed to explain the prediction results. The model’s accuracy was validated on classification tasks. The results demonstrate that the ensemble learning-based predictive framework significantly outperforms conventional machine learning methods. Through feature importance analysis, the SHAP method enhances model interpretability and improves the reliability of the prediction results, enabling more personalized interventions to support students. ","manuscriptTitle":"Predicting Learning Achievement Using Ensemble Learning with Result Explanation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-26 01:39:16","doi":"10.21203/rs.3.rs-4674228/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":"cbdf4997-eabd-4317-908e-b217a97ba9f1","owner":[],"postedDate":"July 26th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":35117474,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":35117475,"name":"Physical sciences/Mathematics and computing/Information technology"}],"tags":[],"updatedAt":"2024-08-08T11:44:17+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-26 01:39:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4674228","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4674228","identity":"rs-4674228","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}