AI in Stock Market Forecasting: A Systematic Review of Regional Performance, Crisis Robustness, and Transfer Learning

AI in Stock Market Forecasting: A Systematic Review of Regional Performance, Crisis Robustness, and Transfer Learning | 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 AI in Stock Market Forecasting: A Systematic Review of Regional Performance, Crisis Robustness, and Transfer Learning Siddharth Jain, Kamalpreet Kaur This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9471391/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract The application of artificial intelligence to predict stock market movements has grown substantially; however, advancements in algorithms do not always yield better practical decisions for market participants. In this review, we examine 59 primary empirical investigations, drawn from a broader pool of 92 sources, focusing on seven key areas: regional differences in performance, the use of hybrid models, the integration of diverse data modalities, designs that explicitly account for risk, inconsistencies in evaluation metrics, resilience during market crises, and the transferability of learning across different markets. Our findings indicate that the success of a model heavily depends on the specific market context. Furthermore, systems designed to balance predictive accuracy with risk management offer more tangible benefits than those focused solely on getting the forecast right. Notably, dual-output models that incorporate risk awareness demonstrate enhanced risk-adjusted returns, yielding roughly an 18% proportional improvement in Sharpe ratio metrics alongside reduced drawdowns. We also identify a critical issue regarding the misalignment of metrics: evaluating models via RMSE or simple directional accuracy often fails to correlate with true financial utility, thereby complicating efforts to compare studies. We recommend that subsequent research enforce the simultaneous reporting of statistical and financial performance, implement rigorous stress tests for crisis scenarios, and prioritize interpretability to meet regulatory standards. Neglecting these measures could lead to widespread AI adoption inadvertently heightening market vulnerability due to synchronized algorithmic behavior, rather than promoting stability. Stock Market Forecasting Cross-Market Transfer Learning Machine Learning Models Regional Market Heterogeneity Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 10 May, 2026 Reviewers agreed at journal 10 May, 2026 Reviews received at journal 09 May, 2026 Reviewers agreed at journal 08 May, 2026 Reviewers agreed at journal 07 May, 2026 Reviewers agreed at journal 07 May, 2026 Reviewers agreed at journal 05 May, 2026 Reviewers invited by journal 05 May, 2026 Editor assigned by journal 30 Apr, 2026 Submission checks completed at journal 21 Apr, 2026 First submitted to journal 20 Apr, 2026 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-9471391","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":638239988,"identity":"22ebcde0-289f-46f9-9064-8f4fa9be12bc","order_by":0,"name":"Siddharth Jain","email":"data:image/png;base64,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","orcid":"","institution":"Lovely Professional University","correspondingAuthor":true,"prefix":"","firstName":"Siddharth","middleName":"","lastName":"Jain","suffix":""},{"id":638239990,"identity":"fc17719d-ced4-46e5-b7e5-343a6d93210b","order_by":1,"name":"Kamalpreet Kaur","email":"","orcid":"","institution":"Lovely Professional University","correspondingAuthor":false,"prefix":"","firstName":"Kamalpreet","middleName":"","lastName":"Kaur","suffix":""}],"badges":[],"createdAt":"2026-04-20 11:24:03","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9471391/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9471391/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109222274,"identity":"92b2c224-3909-4cad-91ce-285330356377","added_by":"auto","created_at":"2026-05-13 21:06:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2313541,"visible":true,"origin":"","legend":"","description":"","filename":"AIinStockMarketForecasting.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9471391/v1_covered_75e6ece5-1992-4741-9ba5-214c782e004e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"AI in Stock Market Forecasting: A Systematic Review of Regional Performance, Crisis Robustness, and Transfer Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"artificial-intelligence-review","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aire","sideBox":"Learn more about [Artificial Intelligence Review](http://link.springer.com/journal/10462)","snPcode":"10462","submissionUrl":"https://submission.nature.com/new-submission/10462/3","title":"Artificial Intelligence Review","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Stock Market Forecasting, Cross-Market Transfer Learning, Machine Learning Models, Regional Market Heterogeneity","lastPublishedDoi":"10.21203/rs.3.rs-9471391/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9471391/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe application of artificial intelligence to predict stock market movements has grown substantially; however, advancements in algorithms do not always yield better practical decisions for market participants. In this review, we examine 59 primary empirical investigations, drawn from a broader pool of 92 sources, focusing on seven key areas: regional differences in performance, the use of hybrid models, the integration of diverse data modalities, designs that explicitly account for risk, inconsistencies in evaluation metrics, resilience during market crises, and the transferability of learning across different markets. Our findings indicate that the success of a model heavily depends on the specific market context. Furthermore, systems designed to balance predictive accuracy with risk management offer more tangible benefits than those focused solely on getting the forecast right. Notably, dual-output models that incorporate risk awareness demonstrate enhanced risk-adjusted returns, yielding roughly an 18% proportional improvement in Sharpe ratio metrics alongside reduced drawdowns. We also identify a critical issue regarding the misalignment of metrics: evaluating models via RMSE or simple directional accuracy often fails to correlate with true financial utility, thereby complicating efforts to compare studies. We recommend that subsequent research enforce the simultaneous reporting of statistical and financial performance, implement rigorous stress tests for crisis scenarios, and prioritize interpretability to meet regulatory standards. Neglecting these measures could lead to widespread AI adoption inadvertently heightening market vulnerability due to synchronized algorithmic behavior, rather than promoting stability.\u003c/p\u003e","manuscriptTitle":"AI in Stock Market Forecasting: A Systematic Review of Regional Performance, Crisis Robustness, and Transfer Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-13 17:54:20","doi":"10.21203/rs.3.rs-9471391/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"11356460786752277353930793635164505973","date":"2026-05-11T00:59:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"334089627707218503449518206790238748975","date":"2026-05-10T16:14:15+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T08:58:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"339020090756314466794860290359405984109","date":"2026-05-08T06:39:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"116475297274817965001875150923620207040","date":"2026-05-07T13:52:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"152043339030465469637499497215297045404","date":"2026-05-07T12:54:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"289070969901462048627777145674007157694","date":"2026-05-05T15:25:47+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-05-05T12:49:21+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-30T12:09:00+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-21T11:22:33+00:00","index":"","fulltext":""},{"type":"submitted","content":"Artificial Intelligence Review","date":"2026-04-20T11:14:05+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"artificial-intelligence-review","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aire","sideBox":"Learn more about [Artificial Intelligence Review](http://link.springer.com/journal/10462)","snPcode":"10462","submissionUrl":"https://submission.nature.com/new-submission/10462/3","title":"Artificial Intelligence Review","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"6f3a625d-7e19-48b9-bfe0-7fc7995fad49","owner":[],"postedDate":"May 13th, 2026","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"11356460786752277353930793635164505973","date":"2026-05-11T00:59:06+00:00","index":56,"fulltext":""},{"type":"reviewerAgreed","content":"334089627707218503449518206790238748975","date":"2026-05-10T16:14:15+00:00","index":53,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T08:58:08+00:00","index":52,"fulltext":""},{"type":"reviewerAgreed","content":"339020090756314466794860290359405984109","date":"2026-05-08T06:39:28+00:00","index":51,"fulltext":""},{"type":"reviewerAgreed","content":"116475297274817965001875150923620207040","date":"2026-05-07T13:52:53+00:00","index":49,"fulltext":""},{"type":"reviewerAgreed","content":"152043339030465469637499497215297045404","date":"2026-05-07T12:54:55+00:00","index":47,"fulltext":""},{"type":"reviewerAgreed","content":"289070969901462048627777145674007157694","date":"2026-05-05T15:25:47+00:00","index":44,"fulltext":""},{"type":"reviewersInvited","content":"39","date":"2026-05-05T12:49:21+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-30T12:09:00+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-13T17:54:20+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-13 17:54:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9471391","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9471391","identity":"rs-9471391","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}