Improving Employee Retention with Machine Learning for Proactive Turnover Risk Detection and Strategic Interventions

Improving Employee Retention with Machine Learning for Proactive Turnover Risk Detection and Strategic Interventions | 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 Improving Employee Retention with Machine Learning for Proactive Turnover Risk Detection and Strategic Interventions Ying Xu, Zixiang Zhao, Muhammad Shahzad, Nan Niu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8378596/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 14 You are reading this latest preprint version Abstract Employee retention is a significant challenge that faces organizations today due to its influence on workforce stability, employee productivity, and business success. The existing approaches employed by organizations, such as engagement surveys and interviews in case of exit, are not effective in predicting employee retention accurately based on the principle of reactivity. The weaknesses in machine learning (ML) enable companies to formulate prediction models on employee retention risks in advance. The acquired data will offer a science-driven staff retention framework that forecasts the likelihood of employees leaving and the most critical factors causing a worker to quit their job based on ML methodologies. Human resource (HR) records are used to evaluate three monitored learning models, such as logistic regression, random forests, and gradient boosting machine (GBM), and to assess their capacity to predict employee departures. A large company provided 10,248 records of its employees with 35 variables to analyze. Preprocessing of the data involved normalization, feature selection, and exploratory analysis. The training made use of an 80-20 split between training and testing data, and they utilized cross-validation techniques to guarantee their resistance to errors. Accuracy, precision, recall, F1-score, and AUC-ROC were the measures that were used in the model evaluation. The analysis of feature importance has identified three key factors that contribute to turnover: remuneration, tenure, and engagement scores. GBM achieved better performance than other models with an 87.7% F1 Score and a 0.94 AUC-ROC score. Risky employees have been identified, and thus, appropriate HR interventions have been done. The ML framework assists organizations in engaging in proactive steps to employee retention by using data-driven strategies to mitigate the risks of employee turnover. Models will be refined and improved with real-time data to enhance the prediction of the future. Physical sciences/Mathematics and computing Health sciences/Risk factors Employee Retention Machine Learning Turnover Prediction Human Resource Analytics Gradient Boosting Predictive Modeling Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 21 Apr, 2026 Reviews received at journal 03 Apr, 2026 Reviews received at journal 12 Mar, 2026 Reviewers agreed at journal 07 Mar, 2026 Reviews received at journal 06 Mar, 2026 Reviewers agreed at journal 06 Mar, 2026 Reviews received at journal 05 Mar, 2026 Reviewers agreed at journal 05 Mar, 2026 Reviewers agreed at journal 05 Mar, 2026 Reviewers invited by journal 05 Feb, 2026 Editor assigned by journal 30 Jan, 2026 Editor invited by journal 20 Jan, 2026 Submission checks completed at journal 09 Jan, 2026 First submitted to journal 09 Jan, 2026 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-8378596","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":586307789,"identity":"60d5065a-336a-446d-a83a-31d1eda67c52","order_by":0,"name":"Ying Xu","email":"","orcid":"","institution":"Jilin University","correspondingAuthor":false,"prefix":"","firstName":"Ying","middleName":"","lastName":"Xu","suffix":""},{"id":586307793,"identity":"1605e615-502d-48e1-90b9-1dee5330b692","order_by":1,"name":"Zixiang Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/0lEQVRIiWNgGAWjYDACCRBhwMADJBkfSBgwQLjEamE2IEELBLDB2Pi1yM9ufvjwR8FhGf7Z7dcqLArqEhvYm7dJMNTcwamFcc4xY6B70ngk7pwpuyFhcDixgedYmQTDsWc4tTBLJJhJGBjY8DDcyEkDajmQ2CCRYybB2HAYpxY2ifRvEgkGEjzyQC0FEgZAh8m/wa+FB2TmAaAtBjfSjzFIGDADbeHBr0VCIqfYsAHoF8MbOcwSQL8Yt/GkFVskHMOtRX5G+saHP/4ctpe7kf7ws8SfOtl+9sMbb3yowa0F2Y0GzKCIYQOxE4jRwMDA/oDxA3EqR8EoGAWjYIQBADpLTOB52b0eAAAAAElFTkSuQmCC","orcid":"","institution":"Jilin University","correspondingAuthor":true,"prefix":"","firstName":"Zixiang","middleName":"","lastName":"Zhao","suffix":""},{"id":586307796,"identity":"25716f19-b3fa-453a-9c20-d4549b09cc6e","order_by":2,"name":"Muhammad Shahzad","email":"","orcid":"","institution":"Northeast Normal University","correspondingAuthor":false,"prefix":"","firstName":"Muhammad","middleName":"","lastName":"Shahzad","suffix":""},{"id":586307797,"identity":"cee0746a-596b-4db6-a8de-3dc14f165b5c","order_by":3,"name":"Nan Niu","email":"","orcid":"","institution":"Harbin Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Nan","middleName":"","lastName":"Niu","suffix":""}],"badges":[],"createdAt":"2025-12-16 17:08:44","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8378596/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8378596/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102217786,"identity":"9d5a6ef9-369b-4f72-b1f7-b5d92d17ba6a","added_by":"auto","created_at":"2026-02-09 13:12:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1519500,"visible":true,"origin":"","legend":"","description":"","filename":"AnonymizedUpdatedVersion.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8378596/v1_covered_82fc1eaf-d317-4460-a477-b50a3f957b42.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Improving Employee Retention with Machine Learning for Proactive Turnover Risk Detection and Strategic Interventions","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"humanities-and-social-sciences-communications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"palcomms","sideBox":"Learn more about [Humanities \u0026 Social Sciences Communications](http://www.nature.com/palcomms/)","snPcode":"41599","submissionUrl":"https://submission.springernature.com/new-submission/41599/3","title":"Humanities and Social Sciences Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Nature AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Employee Retention, Machine Learning, Turnover Prediction, Human Resource Analytics, Gradient Boosting, Predictive Modeling","lastPublishedDoi":"10.21203/rs.3.rs-8378596/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8378596/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Employee retention is a significant challenge that faces organizations today due to its influence on workforce stability, employee productivity, and business success. The existing approaches employed by organizations, such as engagement surveys and interviews in case of exit, are not effective in predicting employee retention accurately based on the principle of reactivity. The weaknesses in machine learning (ML) enable companies to formulate prediction models on employee retention risks in advance. The acquired data will offer a science-driven staff retention framework that forecasts the likelihood of employees leaving and the most critical factors causing a worker to quit their job based on ML methodologies. Human resource (HR) records are used to evaluate three monitored learning models, such as logistic regression, random forests, and gradient boosting machine (GBM), and to assess their capacity to predict employee departures. A large company provided 10,248 records of its employees with 35 variables to analyze. Preprocessing of the data involved normalization, feature selection, and exploratory analysis. The training made use of an 80-20 split between training and testing data, and they utilized cross-validation techniques to guarantee their resistance to errors. Accuracy, precision, recall, F1-score, and AUC-ROC were the measures that were used in the model evaluation. The analysis of feature importance has identified three key factors that contribute to turnover: remuneration, tenure, and engagement scores. GBM achieved better performance than other models with an 87.7% F1 Score and a 0.94 AUC-ROC score. Risky employees have been identified, and thus, appropriate HR interventions have been done. The ML framework assists organizations in engaging in proactive steps to employee retention by using data-driven strategies to mitigate the risks of employee turnover. Models will be refined and improved with real-time data to enhance the prediction of the future.","manuscriptTitle":"Improving Employee Retention with Machine Learning for Proactive Turnover Risk Detection and Strategic Interventions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-09 13:10:51","doi":"10.21203/rs.3.rs-8378596/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-21T15:45:27+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-03T06:32:17+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-12T22:09:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"324190813956279061714807518811209133981","date":"2026-03-07T20:57:46+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-07T00:22:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"73654851669661628589676612442712744662","date":"2026-03-07T00:20:12+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-06T04:38:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"120976947893966776684031236462713001993","date":"2026-03-05T13:38:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"326646191219457401112932708299273211355","date":"2026-03-05T13:18:33+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-05T11:18:02+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-30T13:26:12+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-01-20T20:58:42+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-09T19:16:25+00:00","index":"","fulltext":""},{"type":"submitted","content":"Humanities and Social Sciences Communications","date":"2026-01-09T19:10:20+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"humanities-and-social-sciences-communications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"palcomms","sideBox":"Learn more about [Humanities \u0026 Social Sciences Communications](http://www.nature.com/palcomms/)","snPcode":"41599","submissionUrl":"https://submission.springernature.com/new-submission/41599/3","title":"Humanities and Social Sciences Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Nature AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"7d484928-5605-4ca6-be34-31099dd5ca4c","owner":[],"postedDate":"February 9th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":62381017,"name":"Physical sciences/Mathematics and computing"},{"id":62381018,"name":"Health sciences/Risk factors"}],"tags":[],"updatedAt":"2026-05-18T06:09:16+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-09 13:10:51","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8378596","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8378596","identity":"rs-8378596","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}