Implicit Switching-Cost Regularization in Supervised Trading Signal Classification

Implicit Switching-Cost Regularization in Supervised Trading Signal Classification | 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 Implicit Switching-Cost Regularization in Supervised Trading Signal Classification Tomasz Witkowski This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8947769/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 Automated trading systems built on supervised learning optimize prediction accu- racy while ignoring transaction costs. This leads to volatile signals that trigger excessive position changes and destroy profitability. We show that conditioning predictions on the model’s previous output introduces an implicit switching cost into supervised learn- ing, changing the effective optimization problem without modifying the loss function itself. This decision-path dependence reduces position change frequency substantially while maintaining directional accuracy. Using major currency pairs sampled at 15- minute intervals, we find that models conditioned on previous predictions exhibit sta- tistically significant reductions in switching frequency across all tested assets, with no meaningful deterioration in classification accuracy. Transaction cost sensitivity analy- sis demonstrates that this stability advantage mitigates performance degradation under increasing frictions. The implicit emergence of switching cost aversion through archi- tectural design, rather than explicit penalty terms, offers a computationally tractable method for building transaction-cost-aware trading systems within standard supervised learning frameworks. The analysis uses foreign exchange data; we see no reason why the mechanism would not generalize to other asset classes, though empirical verification remains a direction for future work. JEL Classification: C45, C53, G11, G17 Artificial Intelligence and Machine Learning Other Economics Financial Mathematics Supervised learning Transaction costs Trading strategies Neural networks Currency markets 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-8947769","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":595690335,"identity":"268236aa-9a33-4331-8721-bdd5bd5f7cd6","order_by":0,"name":"Tomasz Witkowski","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0001-9648-9098","institution":"University of Economics in Katowice","correspondingAuthor":true,"prefix":"","firstName":"Tomasz","middleName":"","lastName":"Witkowski","suffix":""}],"badges":[],"createdAt":"2026-02-23 13:46:10","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-8947769/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8947769/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":103507503,"identity":"6d5e5d38-9750-49d0-907f-0b5cb92ba518","added_by":"auto","created_at":"2026-02-26 13:41:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4162094,"visible":true,"origin":"","legend":"","description":"","filename":"CoEcon.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8947769/v1_covered_43ee5a80-8300-49e8-9510-4dfaa6fc0c18.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eImplicit Switching-Cost Regularization in Supervised Trading Signal Classification\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Economics in Katowice","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":"Supervised learning, Transaction costs, Trading strategies, Neural networks, Currency markets","lastPublishedDoi":"10.21203/rs.3.rs-8947769/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8947769/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAutomated trading systems built on supervised learning optimize prediction accu- racy while ignoring transaction costs. This leads to volatile signals that trigger excessive position changes and destroy profitability. We show that conditioning predictions on the model’s previous output introduces an implicit switching cost into supervised learn- ing, changing the effective optimization problem without modifying the loss function itself. This decision-path dependence reduces position change frequency substantially while maintaining directional accuracy. Using major currency pairs sampled at 15- minute intervals, we find that models conditioned on previous predictions exhibit sta- tistically significant reductions in switching frequency across all tested assets, with no meaningful deterioration in classification accuracy. Transaction cost sensitivity analy- sis demonstrates that this stability advantage mitigates performance degradation under increasing frictions. The implicit emergence of switching cost aversion through archi- tectural design, rather than explicit penalty terms, offers a computationally tractable method for building transaction-cost-aware trading systems within standard supervised learning frameworks. The analysis uses foreign exchange data; we see no reason why the mechanism would not generalize to other asset classes, though empirical verification remains a direction for future work.\u003c/p\u003e\n\u003cp\u003eJEL Classification: C45, C53, G11, G17\u003c/p\u003e","manuscriptTitle":"Implicit Switching-Cost Regularization in Supervised Trading Signal Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-25 00:44:05","doi":"10.21203/rs.3.rs-8947769/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":"94f7a6ff-ce24-4d71-be86-98d03dc0aad3","owner":[],"postedDate":"February 25th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":63384411,"name":"Artificial Intelligence and Machine Learning"},{"id":63384412,"name":"Other Economics"},{"id":63384413,"name":"Financial Mathematics"}],"tags":[],"updatedAt":"2026-02-25T00:44:05+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-25 00:44:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8947769","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8947769","identity":"rs-8947769","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}