Preventing Group Privacy DisclosureThrough Synthetic Data: An Evaluation of Recommender System Methods

Preventing Group Privacy DisclosureThrough Synthetic Data: An Evaluation of Recommender System Methods | 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 Preventing Group Privacy DisclosureThrough Synthetic Data: An Evaluation of Recommender System Methods Carolina Yépez, Lorena Recalde, Edison Loza-Aguirre This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-1793221/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 Nowadays, both the privacy of the data that feeds information systems and the effects of its improper handling are a matter of concern. Thus, in recommender systems, mitigating the disclosure of user privacy has become an issue of attention given the challenges that this entails. While research on algorithmic strategies to synthesize user ratings has addressed the concealment of user profiles in traditional recommender systems, less work has been done regarding the exposure of preferences and sensitive data in group recommender systems. In this paper, we evaluate two methods used to generate synthetic ratings and how they perform when applied in group recommender systems. Specifically, we apply state-of-the-art privacy-based methods in a group recommender system to introduce synthetic data and to assess whether and to what extent their behavior changes in terms of rating prediction. We performed this by exploring several possible combinations of GRS implementation (strategies used in group creation, size of groups, individual ratings prediction algorithms, preferences on aggregation methods). Our results show that it was possible to hide the information of individual preferences without affecting group recommendation performance while preserving privacy. We also found that CART was the method that synthesized data with the less difference from the original data. We do not find significative influence of strategies for group creation, group size or individual ratings prediction methods. To the best of our knowledge, this work represents the first attempt to use partially synthetic group ratings in GRS. Group recommender systems synthetic data differential privacy CART 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-1793221","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":116439442,"identity":"98840205-c8ab-47d9-9fde-ffc2f331d904","order_by":0,"name":"Carolina Yépez","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDklEQVRIiWNgGAWjYLCCBwZwpg2E4iGkJQGhJY1YLQjmYcJa+NvPPnyQUHBHnkEi+diDD3/Oy5lLNzA+eNvGIMffgF2LxJl0Y4MEg2eGDRJp6YYzeG4bW845wGw4t43BWOIAdi0GDGlsEgkGhxkbJHLMpHkkbiduuJHAJs3bxpC4AYfDDPifgbXYN0jkf5P+Y3CuHqiF/TdQSz1OLRIQWxKBtrBJMyQcSDAA2sIM1IIUjGh+ufGMGeiXw8ltPM/MDXsOJBvunJHYLDnnnIThDBx+4e9PYwQG1GHbfvbkZw9+/LGTN5dIPvjhTZmNPK4QgwM2gQQ2aIAwgtRKEFAPtu8ATMsoGAWjYBSMAlQAALVPVcFYfAYrAAAAAElFTkSuQmCC","orcid":"","institution":"National Polytechnic School","correspondingAuthor":true,"prefix":"","firstName":"Carolina","middleName":"","lastName":"Yépez","suffix":""},{"id":116439444,"identity":"ec10aed7-0e64-4b92-9024-4f3dcb6f0286","order_by":1,"name":"Lorena Recalde","email":"","orcid":"","institution":"National Polytechnic School","correspondingAuthor":false,"prefix":"","firstName":"Lorena","middleName":"","lastName":"Recalde","suffix":""},{"id":116439446,"identity":"5524c9b6-8c11-466a-98cb-26bc2ff5a2d5","order_by":2,"name":"Edison Loza-Aguirre","email":"","orcid":"","institution":"National Polytechnic School","correspondingAuthor":false,"prefix":"","firstName":"Edison","middleName":"","lastName":"Loza-Aguirre","suffix":""}],"badges":[],"createdAt":"2022-06-24 22:59:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-1793221/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-1793221/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":23244634,"identity":"7154e9dc-a4e6-41bf-86b5-43b2089b6f0d","added_by":"auto","created_at":"2022-06-29 17:29:39","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1057859,"visible":true,"origin":"","legend":"","description":"","filename":"PaperpararevistaCarolinaYepezFINAL.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1793221/v1_covered.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Preventing Group Privacy DisclosureThrough Synthetic Data: An Evaluation of Recommender System Methods","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-1793221/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"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":false,"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":"Group recommender systems, synthetic data, differential privacy, CART","lastPublishedDoi":"10.21203/rs.3.rs-1793221/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-1793221/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eNowadays, both the privacy of the data that feeds information systems and the effects of its improper handling are a matter of concern. Thus, in recommender systems, mitigating the disclosure of user privacy has become an issue of attention given the challenges that this entails. While research on algorithmic strategies to synthesize user ratings has addressed the concealment of user profiles in traditional recommender systems, less work has been done regarding the exposure of preferences and sensitive data in group recommender systems. In this paper, we evaluate two methods used to generate synthetic ratings and how they perform when applied in group recommender systems. Specifically, we apply state-of-the-art privacy-based methods in a group recommender system to introduce synthetic data and to assess whether and to what extent their behavior changes in terms of rating prediction. We performed this by exploring several possible combinations of GRS implementation (strategies used in group creation, size of groups, individual ratings prediction algorithms, preferences on aggregation methods). Our results show that it was possible to hide the information of individual preferences without affecting group recommendation performance while preserving privacy. We also found that CART was the method that synthesized data with the less difference from the original data. We do not find significative influence of strategies for group creation, group size or individual ratings prediction methods. To the best of our knowledge, this work represents the first attempt to use partially synthetic group ratings in GRS. \u003c/p\u003e","manuscriptTitle":"Preventing Group Privacy DisclosureThrough Synthetic Data: An Evaluation of Recommender System Methods","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2022-06-29 17:29:34","doi":"10.21203/rs.3.rs-1793221/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":"4e661ebf-dcc1-47e7-bb39-2a72886418ad","owner":[],"postedDate":"June 29th, 2022","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-06-26T04:44:13+00:00","versionOfRecord":[],"versionCreatedAt":"2022-06-29 17:29:34","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-1793221","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-1793221","identity":"rs-1793221","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}