Stock index trend prediction based on multiscale random forests

Stock index trend prediction based on multiscale random forests | 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 Stock index trend prediction based on multiscale random forests Aizhen Ren, Zida Lin, Takashi Ishida, Yutaka Akiyama This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5295641/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 This paper describes the implementation of a multiscale bootstrap method to improve the random forest algorithm. We construct a multiscale random forest model with the aim of enhancing the classification accuracy of the conventional random forest method, and we apply it to stock index predictions. First, the basic indicators of the CSI 300 stock index are analyzed through stepwise regression analysis to obtain a smaller number of input indicators. Second, using the multiscale bootstrap method, the training samples are resampled multiple times during the model construction stage to generate multiple random forests. These random forests are integrated to obtain the multiscale random forest. In the prediction stage, the multiscale bootstrap probability is obtained and the unbiased p-value with third-order accuracy is computed through regression analysis and extrapolation. Finally, we apply the proposed method to the original dataset and to the dataset obtained after stepwise regression analysis. The predictive performance of multiscale random forest, ordinary random forest, support vector machine, and weighted k-nearest neighbors models are evaluated in terms of accuracy, precision, recall, and F1 score. The results show that the proposed multiscale random forest model outperforms the other models on the accuracy, precision, and F1 score metrics when using the first dataset, but gives a worse recall value than the support vector machine model. On the second dataset, the proposed multiscale random forest model achieves the highest precision. Therefore, the multiscale random forest prediction model is suitable for stock index forecasting, providing theoretical and technical support for the subsequent construction of quantitative timing strategies, option pricing models, and financial early-warning models of listed companies for higher-level theoretical research and development of new application systems. Multiscale bootstrap method Random forest Stock index forecasting Full Text Additional Declarations No competing interests reported. Supplementary Files Supportinginformation.zip DESCRIIJACM.pdf 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-5295641","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":370183963,"identity":"09301bfd-1ccc-4e64-af4b-f9f815c95864","order_by":0,"name":"Aizhen Ren","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA30lEQVRIie3RsQrCMBCA4SsBu0TieKLQV7gi1MWHCRTapbO4WRB00b0+h+CcySk4d+zUqYOTOBS0COqW1k0w3xIy/JeEAFjW77ozAdB77WSXhLnD9NtEkPokZtPNTsGt7o0meVgWlwV4zQ3LwpSM9Vk6W84nQR5N/UyDv08hJlOCmBBwxDDIZTDqr0E2N4zQmHgVOTXR8pDF144JcmJcSkaYdD2FJ8TGSjHU1XyYafT3q7a3uJqcqlZMbOIjXhYzT7jbqDAlDff2XAbyOaL5Ix61FC9CvWecOiaWZVl/4gGvoD3AfY9eEwAAAABJRU5ErkJggg==","orcid":"","institution":"Inner Mengolia Agricultural University","correspondingAuthor":true,"prefix":"","firstName":"Aizhen","middleName":"","lastName":"Ren","suffix":""},{"id":370183964,"identity":"501d831d-e9c1-4319-a01b-1ae0987d3e44","order_by":1,"name":"Zida Lin","email":"","orcid":"","institution":"Inner Mengolia Agricultural University","correspondingAuthor":false,"prefix":"","firstName":"Zida","middleName":"","lastName":"Lin","suffix":""},{"id":370183966,"identity":"3fd61fd7-5e7d-4b5a-96cb-7c91443fa1b7","order_by":2,"name":"Takashi Ishida","email":"","orcid":"","institution":"Tokyo Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Takashi","middleName":"","lastName":"Ishida","suffix":""},{"id":370183967,"identity":"cf1c2d04-6b81-4ce8-abd3-a6a628db2599","order_by":3,"name":"Yutaka Akiyama","email":"","orcid":"","institution":"Tokyo Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yutaka","middleName":"","lastName":"Akiyama","suffix":""}],"badges":[],"createdAt":"2024-10-19 17:23:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5295641/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5295641/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":85719064,"identity":"b4b9a092-5030-4f2d-bc7e-2b86f56cbd9e","added_by":"auto","created_at":"2025-07-01 05:01:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":854206,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5295641/v1_covered_c72a2e9b-7a5b-4f82-bf14-a3b3eb94e587.pdf"},{"id":68232061,"identity":"88ac7196-b6a7-4135-b4e7-a3d7c8108da4","added_by":"auto","created_at":"2024-11-05 06:13:05","extension":"zip","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":2530390,"visible":true,"origin":"","legend":"","description":"","filename":"Supportinginformation.zip","url":"https://assets-eu.researchsquare.com/files/rs-5295641/v1/2f86505cc771ffc884bd0fc9.zip"},{"id":68232060,"identity":"3373e91c-1ba2-4d02-9ce8-986b72918226","added_by":"auto","created_at":"2024-11-05 06:13:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":19681,"visible":true,"origin":"","legend":"","description":"","filename":"DESCRIIJACM.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5295641/v1/ac2162e2d67cc244390d418a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Stock index trend prediction based on multiscale random forests","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":"Multiscale bootstrap method, Random forest, Stock index forecasting","lastPublishedDoi":"10.21203/rs.3.rs-5295641/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5295641/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper describes the implementation of a multiscale bootstrap method to improve the random forest algorithm. We construct a multiscale random forest model with the aim of enhancing the classification accuracy of the conventional random forest method, and we apply it to stock index predictions. First, the basic indicators of the CSI 300 stock index are analyzed through stepwise regression analysis to obtain a smaller number of input indicators. Second, using the multiscale bootstrap method, the training samples are resampled multiple times during the model construction stage to generate multiple random forests. These random forests are integrated to obtain the multiscale random forest. In the prediction stage, the multiscale bootstrap probability is obtained and the unbiased p-value with third-order accuracy is computed through regression analysis and extrapolation. Finally, we apply the proposed method to the original dataset and to the dataset obtained after stepwise regression analysis. The predictive performance of multiscale random forest, ordinary random forest, support vector machine, and weighted k-nearest neighbors models are evaluated in terms of accuracy, precision, recall, and F1 score. The results show that the proposed multiscale random forest model outperforms the other models on the accuracy, precision, and F1 score metrics when using the first dataset, but gives a worse recall value than the support vector machine model. On the second dataset, the proposed multiscale random forest model achieves the highest precision. Therefore, the multiscale random forest prediction model is suitable for stock index forecasting, providing theoretical and technical support for the subsequent construction of quantitative timing strategies, option pricing models, and financial early-warning models of listed companies for higher-level theoretical research and development of new application systems.\u003c/p\u003e","manuscriptTitle":"Stock index trend prediction based on multiscale random forests","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-05 06:13:00","doi":"10.21203/rs.3.rs-5295641/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":"0c5864b8-5f3b-4725-8dac-2adffabe3272","owner":[],"postedDate":"November 5th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-07-01T04:53:33+00:00","versionOfRecord":[],"versionCreatedAt":"2024-11-05 06:13:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5295641","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5295641","identity":"rs-5295641","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}