Cohort Revenue & Retention Analysis: A Bayesian Approach 

Cohort Revenue & Retention Analysis: A Bayesian Approach | 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Research Article Cohort Revenue & Retention Analysis: A Bayesian Approach Juan Camilo Orduz This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6507047/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 We present a Bayesian approach to model cohort-level retention rates and revenue over time. We use Bayesian additive regression trees (BART) to model the retention component which we couple with a linear model for the revenue component. This method is flexible enough to allow adding additional covariates to both model components. This Bayesian framework allows us to quantify uncertainty in the estimation, understand the effect of covariates on retention through partial dependence plots (PDP) and individual conditional expectation (ICE) plots, and most importantly, forecast future revenue and retention rates with well-calibrated uncertainty through highest density intervals. We also provide alternative approaches to model the retention component using neural networks and inference through stochastic variational inference. 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-6507047","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":447197348,"identity":"b7e2c769-55b5-47b7-837d-4d2f67da0369","order_by":0,"name":"Juan Camilo Orduz","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4UlEQVRIiWNgGAWjYBACxgYgkQBiHWBgfACkePiI05IA1sJsANLCRpxdEC1sEiA2QS3MM5KfPXj4wyaf70b6s8qvOXYybAzMDx/dwOewGWnmBgkJaZYzbySk3Zbdlgx0GJuxcQ5eLQlmEgkJhw0MbiQcuy25jRmohYdNGr+W9G9QLYltxZLb6onRkgOzJZmN8eO2w0Ro6XlTJpGQlmYgeeYZszTjtuM8bMwE/GLYnr5N8oeNjQHf8fSHH39uq7bnZ29++BivlgYkDjMPmMSjHATkUVz5g4DqUTAKRsEoGJkAABz8Rvqxr61lAAAAAElFTkSuQmCC","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Juan","middleName":"Camilo","lastName":"Orduz","suffix":""}],"badges":[],"createdAt":"2025-04-22 19:53:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6507047/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6507047/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":81919403,"identity":"ef72b529-46ea-401c-bbe8-98d2a8e220d3","added_by":"auto","created_at":"2025-05-04 21:16:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6488818,"visible":true,"origin":"","legend":"","description":"","filename":"cohortrevenueretentionarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6507047/v1_covered_9db53e73-8fb3-4606-ae71-21e90f12b0c0.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Cohort Revenue \u0026 Retention Analysis: A Bayesian Approach ","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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-6507047/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6507047/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWe present a Bayesian approach to model cohort-level retention rates and revenue over time. We use Bayesian additive regression trees (BART) to model the retention component which we couple with a linear model for the revenue component. This method is flexible enough to allow adding additional covariates to both model components. This Bayesian framework allows us to quantify uncertainty in the estimation, understand the effect of covariates on retention through partial dependence plots (PDP) and individual conditional expectation (ICE) plots, and most importantly, forecast future revenue and retention rates with well-calibrated uncertainty through highest density intervals. We also provide alternative approaches to model the retention component using neural networks and inference through stochastic variational inference.\u003c/p\u003e","manuscriptTitle":"Cohort Revenue \u0026amp; Retention Analysis: A Bayesian Approach ","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-29 02:24:44","doi":"10.21203/rs.3.rs-6507047/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":"3e265fca-aa4b-45c8-b77e-09810889120f","owner":[],"postedDate":"April 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-05-04T21:08:19+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-29 02:24:44","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6507047","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6507047","identity":"rs-6507047","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}