Do Kolmogorov-arnold Networks Have Great Genes? An Application to Sydney’s Housing Market

Do Kolmogorov-arnold Networks Have Great Genes? An Application to Sydney’s Housing Market | 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 Do Kolmogorov-arnold Networks Have Great Genes? An Application to Sydney’s Housing Market GENARO DAMIANI, Tomás Kairuz, SERENA LANUSSE This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9172341/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 benchmark Kolmogorov-Arnold Networks (KANs) against thirteen alternative methods—regularized linear, kernel, tree-based, and neural—for predicting suburb-level relative prices in Sydney’s housing market. Our data cover 2.5 million residential sales across 963 suburbs over 2001–2025, aggregated to suburb-level relative prices defined as the ratio of each suburb’s median sale price to the Greater Sydney median. A standardized evaluation design—common predictor set, common tuning protocol, and common cross-validation scheme—isolates model effects from data effects across two time horizons: a 25-year crosssection and a 5-year panel. Gradient-boosted trees dominate at both horizons, consistent with prior evidence on tree-based superiority for tabular data. Despite a stronger theoretical foundation—the Kolmogorov-Arnold Representation Theorem guarantees exact decomposition of any continuous function into univariate components—KANs never rank in the top four and are the most computationally expensive method. The bottleneck is not the theorem but its implementation: gradient descent on B-spline coefficients offers no guarantee of recovering the exact decomposition. Housing Market Kolmogorov-Arnold Networks Machine Learning Deep Learning Property Prices 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-9172341","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":611419972,"identity":"bae96c43-bb56-4c32-9000-46dc86cc1ff1","order_by":0,"name":"GENARO DAMIANI","email":"","orcid":"","institution":"University of San Andrés","correspondingAuthor":false,"prefix":"","firstName":"GENARO","middleName":"","lastName":"DAMIANI","suffix":""},{"id":611419974,"identity":"c5f00268-a5c0-4ce3-b595-04dfe3a7c005","order_by":1,"name":"Tomás Kairuz","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIiWNgGAWjYDACHgaGA0BKjoEhAcxnbCCoA6rFmDQtIJDYQLQWe57DDw9XttWlbziefPjDDwYb2Q0HmJ99wGsLb5vBwbNtbLkbzjxLk+xhSDPecIDNeAZeLfwMBgcb23hyN9zIMQOGxeHEDQdAHsOrhf0DUItEusGN/M8f/zD8B2ph/4xfC28PyBaDBIMbOQzSPAwHgFp4CNhy5kzBwYZzCYYzzzwzk5YxSDaeeZinGK8W9p70zR8byurk+Y4nP/74psJOtu94+2a8WtCAARAzk6JhFIyCUTAKRgFWAAB/BExSIeCR7AAAAABJRU5ErkJggg==","orcid":"","institution":"University of San Andrés","correspondingAuthor":true,"prefix":"","firstName":"Tomás","middleName":"","lastName":"Kairuz","suffix":""},{"id":611419975,"identity":"7fcaa998-93c8-49e6-8723-a39c4f0f4a70","order_by":2,"name":"SERENA LANUSSE","email":"","orcid":"","institution":"University of San Andrés","correspondingAuthor":false,"prefix":"","firstName":"SERENA","middleName":"","lastName":"LANUSSE","suffix":""}],"badges":[],"createdAt":"2026-03-19 18:38:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9172341/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9172341/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106094259,"identity":"ed106e1c-4093-4536-bdb1-433626ab46c4","added_by":"auto","created_at":"2026-04-03 11:41:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3888567,"visible":true,"origin":"","legend":"","description":"","filename":"TrabajoFinalBigData8.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9172341/v1_covered_699a7cb3-847c-4455-b1b2-75b622318592.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eDo Kolmogorov-arnold Networks Have Great Genes? An Application to Sydney’s Housing Market\u003c/p\u003e","fulltext":[],"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":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":"Housing Market, Kolmogorov-Arnold Networks, Machine Learning, Deep Learning, Property Prices","lastPublishedDoi":"10.21203/rs.3.rs-9172341/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9172341/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"We benchmark Kolmogorov-Arnold Networks (KANs) against thirteen alternative methods—regularized linear, kernel, tree-based, and neural—for predicting suburb-level relative prices in Sydney’s housing market. Our data cover 2.5 million residential sales across 963 suburbs over 2001–2025, aggregated to suburb-level relative prices defined as the ratio of each suburb’s median sale price to the Greater Sydney median. A standardized evaluation design—common predictor set, common tuning protocol, and common cross-validation scheme—isolates model effects from data effects across two time horizons: a 25-year crosssection and a 5-year panel. Gradient-boosted trees dominate at both horizons, consistent with prior evidence on tree-based superiority for tabular data. Despite a stronger theoretical foundation—the Kolmogorov-Arnold Representation Theorem guarantees exact decomposition of any continuous function into univariate components—KANs never rank in the top four and are the most computationally expensive method. The bottleneck is not the theorem but its implementation: gradient descent on B-spline coefficients offers no guarantee of recovering the exact decomposition.","manuscriptTitle":"Do Kolmogorov-arnold Networks Have Great Genes? An Application to Sydney’s Housing Market","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-02 19:49:23","doi":"10.21203/rs.3.rs-9172341/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":"33286b89-6e3b-4094-a02a-6108a022a4b7","owner":[],"postedDate":"April 2nd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-02T19:49:23+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-02 19:49:23","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9172341","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9172341","identity":"rs-9172341","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}