Improving Automotive Production Forecasts via Explainable AI-Driven Feature Pruning

Improving Automotive Production Forecasts via Explainable AI-Driven Feature Pruning | 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 Improving Automotive Production Forecasts via Explainable AI-Driven Feature Pruning James AmRhine Ferreira This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7522021/v2 This work is licensed under a CC BY 4.0 License Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Abstract This research uses explainable AI (XAI) to improve machine learning (ML) models in forecasting production by identifying and pruning low-value sensor-derived features in production forecasting tasks. The methodology entails the initial training of ML models, followed by a fine-tuning phase in which irrelevant features identified through explainability methods are eliminated. It builds on the throughput prediction architecture of BMW by performing XAI-driven refinement on top of an existing Extra Trees ensemble framework. Using Shapley values and permutation importance, redundant, unstable, or low-signal inputs are removed. This reduces overfitting, improves model interpretability, and compresses inference time without sacrificing accuracy. The result is both performance improvements and simplified model logic, enabling potential reductions in manufacturing costs and improved model transparency. Attribution monitoring also enables early detection of deteriorating predictive logic—supporting more transparent, auditable, and adaptable decision-making in automotive manufacturing environments. Artificial Intelligence and Machine Learning Predictive forecasting Explainable artificial intelligence (XAI) Feature pruning Automotive manufacturing Sensor/IoT Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 2 posted You are reading this latest preprint version Show more versions 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-7522021","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":510127604,"identity":"f531425e-d869-4f1a-93db-c1a175128853","order_by":0,"name":"James AmRhine Ferreira","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIiWNgGAWjYBAC9gYw9R9MHmBgsEkgqIWxAaYYQqaRqAUIDhOhpf104sMfDAfkzGcfPni4ouZ8nu6M7MQPDDU20Ti19ORuNuZh+GMscy4t4eCZY7eLzW7kbpZgOJaW24DTYbnbpIEOS5zBw2NwsIHtduK227nbgMKHcWvpf7v9J9Bh9TN4+D8cbPh3jrAWwRlABTwMBxIkeHgYDja2HSCsRVri7WZpHoMDhjN42AwONvYlF5vdf7tZIgGPX/j4czd+/FFxQF6Ch/nxx4ZvdnlmZ85u/PChxganFggwQBdIwKt8FIyCUTAKRgEhAACjsWKoMdXvsgAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0009-0001-5550-0702","institution":"BMW Group, University of Rochester","correspondingAuthor":true,"prefix":"","firstName":"James","middleName":"AmRhine","lastName":"Ferreira","suffix":""}],"badges":[],"createdAt":"2025-09-03 02:41:34","currentVersionCode":2,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7522021/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-7522021/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90693723,"identity":"b06b035d-75e6-4564-b68e-ce7dce29ba6c","added_by":"auto","created_at":"2025-09-05 19:20:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":419016,"visible":true,"origin":"","legend":"","description":"","filename":"ImprovingAutomotiveProductionForecastsviaExplainableAIDrivenFeaturePruningSpringer.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7522021/v2_covered_9fb3557b-447c-4156-b883-5b50a6cdfa36.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"Improving Automotive Production Forecasts via Explainable AI-Driven Feature Pruning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"BMW Group","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":"Predictive forecasting, Explainable artificial intelligence (XAI), Feature pruning, Automotive manufacturing, Sensor/IoT","lastPublishedDoi":"10.21203/rs.3.rs-7522021/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7522021/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis research uses explainable AI (XAI) to improve machine learning (ML) models in forecasting production by identifying and pruning low-value sensor-derived features in production forecasting tasks. The methodology entails the initial training of ML models, followed by a fine-tuning phase in which irrelevant features identified through explainability methods are eliminated. It builds on the throughput prediction architecture of BMW by performing XAI-driven refinement on top of an existing Extra Trees ensemble framework. Using Shapley values and permutation importance, redundant, unstable, or low-signal inputs are removed. This reduces overfitting, improves model interpretability, and compresses inference time without sacrificing accuracy. The result is both performance improvements and simplified model logic, enabling potential reductions in manufacturing costs and improved model transparency. Attribution monitoring also enables early detection of deteriorating predictive logic\u0026mdash;supporting more transparent, auditable, and adaptable decision-making in automotive manufacturing environments.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e","manuscriptTitle":"Improving Automotive Production Forecasts via Explainable AI-Driven Feature Pruning","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2025-09-05 18:48:48","doi":"10.21203/rs.3.rs-7522021/v2","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}},{"code":1,"date":"2025-09-04 09:04:10","doi":"10.21203/rs.3.rs-7522021/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":"e7055603-1e0f-4c2a-a6e2-8c4d67a0c8ae","owner":[],"postedDate":"September 5th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":54182912,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-12-18T13:42:08+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-05 18:48:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-7522021","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7522021","identity":"rs-7522021","version":["v2"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}