Modeling the Frequency and Severity of Auto Insurance Claims using Machine Learning Techniques

Modeling the Frequency and Severity of Auto Insurance Claims using Machine Learning Techniques | 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 Modeling the Frequency and Severity of Auto Insurance Claims using Machine Learning Techniques Samuel M Nuugulu, Ruvarashe Mutasa This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6178099/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 The auto insurance industry constantly seeks innovative approahes to accurately predict and manage both the frequency and severity of insurance claims. This study delves into leveraging machine learning techniques to model insurance claims, focusing on estimating the frequency and severity of claims. A comprehensive dataset encompassing a wide array of variables related to policyholders, vehicles, accidents, and historical claims was used to train and validate the machine learning models. For a frequency prediction, models such as poisson regression, decision tress, random forests, and gradient boosting were employed to estimate the likelihood of a claim occurence. The severity prediction entailed the application of regression-based models, such as linear regression and decision trees, for the purpose of forecasting the financial magnitude of claims in the event of their occurrence. The results demonstrate the efficacy of machine learning in accurately predicting the frequency and severity of auto insurance claims. The predictive models achieved notable accuracy and performance metrics, aiding insurers in assesing risk, setting premiums, and optimizing their claim handling processes. Moreover, this study illuminates the prospect of augmenting decision-making and risk management capabilities in the automobile insurance sector by incorporating advanced machine learning methodologies. Mathematics Subject Classification: 34A08, 65M06, 65N12, 35R11. Artificial Intelligence and Machine Learning Machine Learning Auto Insurance Claim Modelling Full Text Additional Declarations The authors declare no competing interests. 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-6178099","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":425582717,"identity":"47f30428-0bae-465a-b938-e155d0b1ee8a","order_by":0,"name":"Samuel M Nuugulu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAt0lEQVRIiWNgGAWjYPACCwZ+UrVIMEg2kKzF4ACxauVn95hJfm2TSNx8I/fgpxsMd+QJajG4c8ZMWhaoZduNvGTpHIZnhgQdaCCRYyYtCdaSYwDUcpiRoBb5GVAtm2fkGP8GarEnqIXhRo6Z5Eeglg0g64BaEgk77EZasTXDOQnjGWfemFnnGBxOJsJhyRtv/iizke1vzzG+nVNx2Jaww4CAmQdhKTHqgYDxB5EKR8EoGAWjYIQCAKeYOiL4cf37AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0003-3966-5088","institution":"University of Namibia","correspondingAuthor":true,"prefix":"","firstName":"Samuel","middleName":"M","lastName":"Nuugulu","suffix":""},{"id":425582718,"identity":"10d14a20-6388-400f-b410-651560a899ae","order_by":1,"name":"Ruvarashe Mutasa","email":"","orcid":"","institution":"University of Namibia","correspondingAuthor":false,"prefix":"","firstName":"Ruvarashe","middleName":"","lastName":"Mutasa","suffix":""}],"badges":[],"createdAt":"2025-03-07 12:01:23","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6178099/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6178099/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":78107847,"identity":"88069d44-ed78-45a0-984f-c313b6241472","added_by":"auto","created_at":"2025-03-10 04:10:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1178714,"visible":true,"origin":"","legend":"","description":"","filename":"RuvapaperFinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6178099/v1_covered_37987289-7f51-444e-b6fb-13152cbde1a1.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eModeling the Frequency and Severity of Auto Insurance Claims using Machine Learning Techniques\u003c/p\u003e","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":"Machine Learning, Auto Insurance, Claim Modelling","lastPublishedDoi":"10.21203/rs.3.rs-6178099/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6178099/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe auto insurance industry constantly seeks innovative approahes to accurately predict and manage both the frequency and severity of insurance claims. This study delves into leveraging machine learning techniques to model insurance claims, focusing on estimating the frequency and severity of claims. A comprehensive dataset encompassing a wide array of variables related to policyholders, vehicles, accidents, and historical claims was used to train and validate the machine learning models. For a frequency prediction, models such as poisson regression, decision tress, random forests, and gradient boosting were employed to estimate the likelihood of a claim occurence. The severity prediction entailed the application of regression-based models, such as linear regression and decision trees, for the purpose of forecasting the financial magnitude of claims in the event of their occurrence. The results demonstrate the efficacy of machine learning in accurately predicting the frequency and severity of auto insurance claims. The predictive models achieved notable accuracy and performance metrics, aiding insurers in assesing risk, setting premiums, and optimizing their claim handling processes. Moreover, this study illuminates the prospect of augmenting decision-making and risk management capabilities in the automobile insurance sector by incorporating advanced machine learning methodologies.\u003c/p\u003e\n\u003cp\u003eMathematics Subject Classification: 34A08, 65M06, 65N12, 35R11.\u003c/p\u003e","manuscriptTitle":"Modeling the Frequency and Severity of Auto Insurance Claims using Machine Learning Techniques","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-10 04:02:09","doi":"10.21203/rs.3.rs-6178099/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":"3820efdb-9a47-4872-bb9c-275d519fd656","owner":[],"postedDate":"March 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":45359270,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-03-10T04:02:09+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-10 04:02:09","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6178099","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6178099","identity":"rs-6178099","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}