Generating Multiperspective Process Traces Using Conditional Variational Autoencoders

Generating Multiperspective Process Traces Using Conditional Variational Autoencoders | 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 Generating Multiperspective Process Traces Using Conditional Variational Autoencoders Riccardo Graziosi, Massimiliano Ronzani, Andrei Buliga, Chiara Di Francescomarino, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5653604/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract In recent years, trace generation has emerged as a significant challenge within the Process Mining community. Deep Learning (DL) models have demonstrated accuracy in reproducing the features of the selected processes. However, current DL generative models are limited in their ability to adapt the learned distributions to generate data samples based on specific conditions or attributes. This limitation is particularly significant because the ability to control the type of generated data can be beneficial in various contexts, enabling a focus on specific behaviours, exploration of infrequent patterns, or simulation of alternative “whatif” scenarios. Moreover, many existing models primarily focus on generating traces that capture only the control-flow and temporal perspectives, neglecting crucial aspects such as resource and data perspectives, which are essential to understanding business process executions. In this work, we address these challenges by introducing a conditional model for multiperspective process data generation based on a conditional variational autoencoder (CVAE). Conditional models offer control over the generation process by tuning input conditional variables, enabling more targeted and controlled data generation. Unlike other domains, CVAE for process mining faces specific challenges due to the multiperspective nature of the data and the need to adhere to control-flow rules while ensuring data variability. Specifically, we focus on two main objectives: (i) generating complete trace executions that include control flow, temporal data, and other data attributes, with a particular focus on trace attributes and resources, as they are the most common attributes in business processes; and (ii) conditioning the trace generation on specific control flow and temporal conditions, enabling the production of traces that align to the desired execution scenarios defined by the condition context. The generated traces are then evaluated using common metrics for generative model assessment, along with additional metrics to evaluate the quality of the conditional generation. Process Mining Deep Learning Generative AI Conditional models Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 24 Apr, 2025 Reviews received at journal 23 Apr, 2025 Reviews received at journal 15 Apr, 2025 Reviewers agreed at journal 30 Mar, 2025 Reviewers agreed at journal 25 Mar, 2025 Reviewers invited by journal 25 Mar, 2025 Submission checks completed at journal 24 Mar, 2025 First submitted to journal 21 Mar, 2025 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-5653604","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":433662498,"identity":"1266f1ad-11b6-4355-bc69-ae2f0218d71b","order_by":0,"name":"Riccardo Graziosi","email":"","orcid":"","institution":"Fondazione Bruno Kessler","correspondingAuthor":false,"prefix":"","firstName":"Riccardo","middleName":"","lastName":"Graziosi","suffix":""},{"id":433662499,"identity":"99a1213a-fc44-46e4-a7f7-be1b925a731c","order_by":1,"name":"Massimiliano Ronzani","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAp0lEQVRIiWNgGAWjYBADHn7mM8wkapFsyyFRC4PBMWK16M4+fOzhj5o7MsbHeA8bMFQcJqzF7FxauoHEsWc8Zsf4khMYzhCj5QyPmYQB22Ees/s9xgcY24jVkvDvMI9xGw9Qyz9itRxsO8xjwMZjnMDYQJQWtjTJxr7DPBJAvxgkHEsnRgvzMckf3w7b87fxHpb4UGNNWAsqSCBVwygYBaNgFIwC7AAARMw1Avr1TT0AAAAASUVORK5CYII=","orcid":"","institution":"Fondazione Bruno Kessler","correspondingAuthor":true,"prefix":"","firstName":"Massimiliano","middleName":"","lastName":"Ronzani","suffix":""},{"id":433662500,"identity":"14e61bbb-b1d8-4417-806f-eca16fad22f1","order_by":2,"name":"Andrei Buliga","email":"","orcid":"","institution":"Fondazione Bruno Kessler","correspondingAuthor":false,"prefix":"","firstName":"Andrei","middleName":"","lastName":"Buliga","suffix":""},{"id":433662501,"identity":"68ce6ac1-73f3-4052-86e3-5500557bc654","order_by":3,"name":"Chiara Di Francescomarino","email":"","orcid":"","institution":"University of Trento","correspondingAuthor":false,"prefix":"","firstName":"Chiara","middleName":"Di","lastName":"Francescomarino","suffix":""},{"id":433662502,"identity":"b37b798b-5921-4024-adc3-bf6fdd54f335","order_by":4,"name":"Francesco Folino","email":"","orcid":"","institution":"National Research Council","correspondingAuthor":false,"prefix":"","firstName":"Francesco","middleName":"","lastName":"Folino","suffix":""},{"id":433662503,"identity":"975eb63c-ebd4-4d5e-9a10-c2b6d5cc4e76","order_by":5,"name":"Chiara Ghidini","email":"","orcid":"","institution":"Free University of Bozen-Bolzano","correspondingAuthor":false,"prefix":"","firstName":"Chiara","middleName":"","lastName":"Ghidini","suffix":""},{"id":433662504,"identity":"9fe71917-1c66-4a77-b5fb-63193c91fe7c","order_by":6,"name":"Francesca Meneghello","email":"","orcid":"","institution":"Fondazione Bruno Kessler","correspondingAuthor":false,"prefix":"","firstName":"Francesca","middleName":"","lastName":"Meneghello","suffix":""},{"id":433662505,"identity":"4279471d-64d8-4ffb-b75b-601aee9efaeb","order_by":7,"name":"Luigi Pontieri","email":"","orcid":"","institution":"National Research Council","correspondingAuthor":false,"prefix":"","firstName":"Luigi","middleName":"","lastName":"Pontieri","suffix":""}],"badges":[],"createdAt":"2024-12-16 12:08:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5653604/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5653604/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":79237857,"identity":"dc9a46f5-b570-4b8d-9de6-335de4d4fee1","added_by":"auto","created_at":"2025-03-26 04:45:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1312632,"visible":true,"origin":"","legend":"","description":"","filename":"CVAEICPMExtensionrevision.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5653604/v1_covered_519a4efc-e2a1-4dbf-91f1-0e04abae4bd6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Generating Multiperspective Process Traces Using Conditional Variational Autoencoders","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":"process-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Process Science](https://link.springer.com/journal/44311)","snPcode":"44311","submissionUrl":"https://submission.springernature.com/new-submission/44311","title":"Process Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Process Mining, Deep Learning, Generative AI, Conditional models","lastPublishedDoi":"10.21203/rs.3.rs-5653604/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5653604/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn recent years, trace generation has emerged as a significant challenge within the Process Mining community. Deep Learning (DL) models have demonstrated accuracy in reproducing the features of the selected processes. However, current DL generative models are limited in their ability to adapt the learned distributions to generate data samples based on specific conditions or attributes. This limitation is particularly significant because the ability to control the type of generated data can be beneficial in various contexts, enabling a focus on specific behaviours, exploration of infrequent patterns, or simulation of alternative “whatif” scenarios. Moreover, many existing models primarily focus on generating traces that capture only the control-flow and temporal perspectives, neglecting crucial aspects such as resource and data perspectives, which are essential to understanding business process executions.\u003c/p\u003e\n\u003cp\u003eIn this work, we address these challenges by introducing a conditional model for multiperspective process data generation based on a conditional variational autoencoder (CVAE). Conditional models offer control over the generation process by tuning input conditional variables, enabling more targeted and controlled data generation. Unlike other domains, CVAE for process mining faces specific challenges due to the multiperspective nature of the data and the need to adhere to control-flow rules while ensuring data variability. Specifically, we focus on two main objectives: (i) generating complete trace executions that include control flow, temporal data, and other data attributes, with a particular focus on trace attributes and resources, as they are the most common attributes in business processes; and (ii) conditioning the trace generation on specific control flow and temporal conditions, enabling the production of traces that align to the desired execution scenarios defined by the condition context. The generated traces are then evaluated using common metrics for generative model assessment, along with additional metrics to evaluate the quality of the conditional generation.\u003c/p\u003e","manuscriptTitle":"Generating Multiperspective Process Traces Using Conditional Variational Autoencoders","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-26 04:36:57","doi":"10.21203/rs.3.rs-5653604/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-04-25T02:04:54+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-23T14:41:55+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-16T01:38:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"171980730555993808988816091201674806396","date":"2025-03-30T23:34:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"103767429508337576507964662332420099642","date":"2025-03-25T09:40:33+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-03-25T04:51:21+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-24T06:04:14+00:00","index":"","fulltext":""},{"type":"submitted","content":"Process Science","date":"2025-03-21T10:27:22+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"process-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Process Science](https://link.springer.com/journal/44311)","snPcode":"44311","submissionUrl":"https://submission.springernature.com/new-submission/44311","title":"Process Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"e20bee7c-042e-4672-91f7-6a67fb686f57","owner":[],"postedDate":"March 26th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-05-08T04:08:36+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-26 04:36:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5653604","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5653604","identity":"rs-5653604","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}