Predicting Tennis Match Outcomes Mid-GameUsing Machine Learning on Psychological and Physical Data

Predicting Tennis Match Outcomes Mid-GameUsing Machine Learning on Psychological and Physical Data | 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 Predicting Tennis Match Outcomes Mid-GameUsing Machine Learning on Psychological and Physical Data Boyuan Li, Zihui Deng, Jinger Li, Yixuan Miao, Gaurav Gupta This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4597222/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 08 Jul, 2025 Read the published version in Journal of Big Data → Version 1 posted 12 You are reading this latest preprint version Abstract Predicting game outcomes has significantly garnered the interest of researchersin recent years. The role of player performance is integral in-game analytics, significantlyimpacting the interpretation and results of the analysis. Quantifyingfactors impacting tennis games would advance the analysis of player’s performance.The proposed work intends to use real-time data from each game pointto determine essential feature values, formulate and assess the impact of psychologicalmomentum, and employ machine learning methodology on mid-matchdata for predicting the game’s victor. The data source is from Wimbledon and US Open games from 2017 to 2022, a total of 1592 games, and utilize 363 gamesof 2023 to evaluate their forecasting ability. We first obtained weights throughinformation entropy and defined psychological momentum, and then 3 best classifiers,random forest, CatBoost, and Logistic Regression, were detected to assessthe features. Additionally, we implemented a soft voting ensemble method integratingthe Random Forest and CatBoost classifiers. All four models achieve over90% accuracy and F1-score, with the soft voting classifier performing the best(accuracy: 97.5%, F1 score: 97.4%). These models achieve predictive accuraciesabove 70% using the first 25% data of a game. Media platforms two-sided markets content provision advertising intensity product differentiation Full Text Additional Declarations No competing interests reported. Appendix A is not available with this version Cite Share Download PDF Status: Published Journal Publication published 08 Jul, 2025 Read the published version in Journal of Big Data → Version 1 posted Editorial decision: Revision requested 23 Dec, 2024 Reviewers agreed at journal 25 Sep, 2024 Reviews received at journal 24 Sep, 2024 Reviewers agreed at journal 19 Sep, 2024 Reviewers agreed at journal 17 Sep, 2024 Reviewers agreed at journal 03 Sep, 2024 Reviews received at journal 30 Aug, 2024 Reviewers agreed at journal 30 Aug, 2024 Reviewers invited by journal 27 Aug, 2024 Editor assigned by journal 16 Jul, 2024 Submission checks completed at journal 03 Jul, 2024 First submitted to journal 18 Jun, 2024 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-4597222","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":330938076,"identity":"8fa2ddbd-7598-45ea-843d-2359b042a628","order_by":0,"name":"Boyuan Li","email":"","orcid":"","institution":"Wenzhou-Kean University","correspondingAuthor":false,"prefix":"","firstName":"Boyuan","middleName":"","lastName":"Li","suffix":""},{"id":330938077,"identity":"8d980e60-96fa-4682-8c62-98548a178e94","order_by":1,"name":"Zihui Deng","email":"","orcid":"","institution":"Wenzhou-Kean University","correspondingAuthor":false,"prefix":"","firstName":"Zihui","middleName":"","lastName":"Deng","suffix":""},{"id":330938078,"identity":"88c2f380-621e-4fd0-8a13-efe0f1f86b16","order_by":2,"name":"Jinger Li","email":"","orcid":"","institution":"Wenzhou-Kean University","correspondingAuthor":false,"prefix":"","firstName":"Jinger","middleName":"","lastName":"Li","suffix":""},{"id":330938079,"identity":"220a2a5e-42c6-498f-a099-b5dcc0a139f3","order_by":3,"name":"Yixuan Miao","email":"","orcid":"","institution":"Hangzhou Normal University","correspondingAuthor":false,"prefix":"","firstName":"Yixuan","middleName":"","lastName":"Miao","suffix":""},{"id":330938080,"identity":"134b0917-f10d-4472-bcbf-d97c4d647604","order_by":4,"name":"Gaurav Gupta","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAs0lEQVRIiWNgGAWjYPACGwMIzUashgMMaaRrOUyCFnn/NWaPP9ScN+ZnP3uA4UPZYcJaDG+8MTc4cOy2mWRPXgLjjHPEaJlxxkziANttG4MDOQbMvG1Ea/l3zsb+/BsD5r/EaJHn7zGTONh2wMxAAmgLIzFaDCTYyg3O9iUbS9x4Y3Cw51w6Ebb0H972oOKbnWF/f47hgx9l1kTYciMBERcHCKsH23KA6BgfBaNgFIyCkQoAzYg9/H0G2JkAAAAASUVORK5CYII=","orcid":"","institution":"Wenzhou-Kean University","correspondingAuthor":true,"prefix":"","firstName":"Gaurav","middleName":"","lastName":"Gupta","suffix":""}],"badges":[],"createdAt":"2024-06-18 04:27:01","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4597222/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4597222/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s40537-025-01216-4","type":"published","date":"2025-07-08T15:57:15+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":86699328,"identity":"712046d3-6f5c-43bd-9de6-7ad78db07bf5","added_by":"auto","created_at":"2025-07-14 16:07:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":507122,"visible":true,"origin":"","legend":"","description":"","filename":"ArticleTitle16.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4597222/v1_covered_82d37320-8abd-4b54-b0f1-1be14d0f8e2c.pdf"}],"financialInterests":"\u003cp\u003eNo competing interests reported.\u003c/p\u003e\n\u003cp\u003eAppendix A is not available with this version\u003c/p\u003e","formattedTitle":"Predicting Tennis Match Outcomes Mid-GameUsing Machine Learning on Psychological and Physical Data","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-big-data","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bigd","sideBox":"Learn more about [Journal of Big Data](http://journalofbigdata.springeropen.com)","snPcode":"40537","submissionUrl":"https://submission.nature.com/new-submission/40537/3","title":"Journal of Big Data","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Media platforms, two-sided markets, content provision, advertising intensity, product differentiation","lastPublishedDoi":"10.21203/rs.3.rs-4597222/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4597222/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Predicting game outcomes has significantly garnered the interest of researchersin recent years. The role of player performance is integral in-game analytics, significantlyimpacting the interpretation and results of the analysis. Quantifyingfactors impacting tennis games would advance the analysis of player’s performance.The proposed work intends to use real-time data from each game pointto determine essential feature values, formulate and assess the impact of psychologicalmomentum, and employ machine learning methodology on mid-matchdata for predicting the game’s victor. The data source is from Wimbledon and US Open games from 2017 to 2022, a total of 1592 games, and utilize 363 gamesof 2023 to evaluate their forecasting ability. We first obtained weights throughinformation entropy and defined psychological momentum, and then 3 best classifiers,random forest, CatBoost, and Logistic Regression, were detected to assessthe features. Additionally, we implemented a soft voting ensemble method integratingthe Random Forest and CatBoost classifiers. All four models achieve over90% accuracy and F1-score, with the soft voting classifier performing the best(accuracy: 97.5%, F1 score: 97.4%). These models achieve predictive accuraciesabove 70% using the first 25% data of a game.","manuscriptTitle":"Predicting Tennis Match Outcomes Mid-GameUsing Machine Learning on Psychological and Physical Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-25 19:26:44","doi":"10.21203/rs.3.rs-4597222/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-12-23T10:28:18+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"76906331284298119817092174219459179673","date":"2024-09-25T09:18:28+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-24T13:42:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"232267746585450494262748424997150074937","date":"2024-09-19T21:49:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"16013472269840331386832385668828304168","date":"2024-09-17T06:20:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"47055200651398908763957931400364284693","date":"2024-09-03T09:49:12+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-30T17:45:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"254638365435360592242703545449031931145","date":"2024-08-30T17:07:44+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-27T16:29:23+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-16T14:05:32+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-03T09:19:39+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Big Data","date":"2024-06-18T04:25:24+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-big-data","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bigd","sideBox":"Learn more about [Journal of Big Data](http://journalofbigdata.springeropen.com)","snPcode":"40537","submissionUrl":"https://submission.nature.com/new-submission/40537/3","title":"Journal of Big Data","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"07c60660-b8a2-4d72-b21e-82e4e1c1fddf","owner":[],"postedDate":"July 25th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-07-14T16:00:36+00:00","versionOfRecord":{"articleIdentity":"rs-4597222","link":"https://doi.org/10.1186/s40537-025-01216-4","journal":{"identity":"journal-of-big-data","isVorOnly":false,"title":"Journal of Big Data"},"publishedOn":"2025-07-08 15:57:15","publishedOnDateReadable":"July 8th, 2025"},"versionCreatedAt":"2024-07-25 19:26:44","video":"","vorDoi":"10.1186/s40537-025-01216-4","vorDoiUrl":"https://doi.org/10.1186/s40537-025-01216-4","workflowStages":[]},"version":"v1","identity":"rs-4597222","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4597222","identity":"rs-4597222","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}