Predicting Tourist Decision-Making Under Data Scarcity: A Hybrid Machine Learning Framework for Digital Marketplaces

Predicting Tourist Decision-Making Under Data Scarcity: A Hybrid Machine Learning Framework for Digital Marketplaces | 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 Predicting Tourist Decision-Making Under Data Scarcity: A Hybrid Machine Learning Framework for Digital Marketplaces Mwapashua H. Fujo, Angel Gabriel Meela This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9515476/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 Understanding and predicting consumer decision-making in digital environments remains a fundamental challenge, particularly in contexts characterized by limited and heterogeneous data. While advances in Machine Learning have enabled significant improvements in behavioral prediction, most existing approaches rely on large-scale datasets, limiting their applicability in real-world settings such as small and medium-sized enterprises (SMEs) and emerging markets. This study proposes a hybrid machine learning framework for predicting tourist decision making under data scarcity conditions in digital marketplaces. The framework integrates ensemble learning and neural modeling to capture both static and temporal behavioral patterns, while incorporating contextual and interaction-based features. Experimental evaluation was conducted using a real-world dataset of 10,000 user sessions collected from a tourism platform in Tanzania. To assess robustness, controlled experiments were performed under varying data availability scenarios. Results demonstrate that the proposed hybrid model consistently outperforms baseline models, achieving superior performance across multiple evaluation metrics, including accuracy, F1-score, and AUC-ROC. Notably, the model maintains strong predictive capability even when trained on reduced datasets, highlighting its robustness in data-constrained environments. Further more, interpretability analysis using Explainable AI reveals key behavioral and contextual factors influencing user decisions. The findings contribute to bridging the gap between advanced predictive analytics and real-world applicability by providing a scalable and adaptable framework for AI-driven decision modeling in low-data environments. The proposed approach has broad implications for digital marketplaces, particularly in emerging economies, where data limitations remain a critical barrier to the adoption of intelligent systems. Artificial Intelligence and Machine Learning Machine Learning Data Scarcity Tourist Behavior Prediction Digital Marketplaces Hybrid Models Explainable AI SME Analytics Predictive Analytics 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-9515476","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":629162748,"identity":"800da02f-d63c-420e-9a0e-0a3d20941d05","order_by":0,"name":"Mwapashua H. Fujo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzElEQVRIiWNgGAWjYBAC9gaGBBDNzw8iEwqI0MJzAKJFcmYDSIsBcVrAQHIDmEGUFomEh48L99hIGJ9fnfjhgQGDPL/YAYJako1nPEuTMLvxdrME0GGGM2cn4NdiL5GQJs1z4HCd2Y2zG0BaEgxuE9DCA9UiYTzj7OYfpGkx4O/dRqQtPA+AfjmQJiFxg3ebRYKBBGG/8LDnJD4uOGAjwd9/dvPNHxU28vzSBLQANSUwg2kJsEoJQspBgP0ARAv/AWJUj4JRMApGwUgEAJQCQmpOsUGmAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-8969-8390","institution":"Moshi Co-operative University (MoCU)","correspondingAuthor":true,"prefix":"","firstName":"Mwapashua","middleName":"H.","lastName":"Fujo","suffix":""},{"id":629162749,"identity":"f422e749-a484-4d16-8825-a8585f704a48","order_by":1,"name":"Angel Gabriel Meela","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAUlEQVRIiWNgGAWjYLCCB0DMx8B84MAHIIONnRgtCSCVDGyJB2eAGMzEa+ExPswD4hHSwj+7/eKDxBwbOTb2AwaHbX5tk+djZmD88DEHtxaJO2eKDRK3pRmz8SQkHM7tu23YxszALDlzGx5rbuSkSSRuO5zYxpBw4HBuz21GoBY2Zl48WuRv5KT/SNz2v76N/2HDYcue2/YEtRjcSD/GkLjtQAKbRDLDYYYftxMJajG8kcMMdFiyYZvEM4aDvQ23k9uYGZvx+kXuRvrDDx+32cnz8+d//vDjz23b+e3NB4EieLzPwGOAYDO2gckGfOqBgP0BEucPAcWjYBSMglEwIgEAK7dWDoyLb+wAAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0005-6524-4019","institution":"Institute of Accountancy Arusha (IAA)","correspondingAuthor":true,"prefix":"","firstName":"Angel","middleName":"Gabriel","lastName":"Meela","suffix":""}],"badges":[],"createdAt":"2026-04-24 09:56:53","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-9515476/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9515476/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107886615,"identity":"e00a8a77-a50d-4cee-b22e-69ec8f6ad215","added_by":"auto","created_at":"2026-04-27 09:30:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":817550,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptPredictingTouristDecisionMakingUnderData.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9515476/v1_covered_a7b350c7-80e9-427a-ae8e-b829523bc31b.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003ePredicting Tourist Decision-Making Under Data Scarcity: A Hybrid Machine Learning Framework for Digital Marketplaces\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, Data Scarcity, Tourist Behavior Prediction, Digital Marketplaces, Hybrid Models, Explainable AI, SME Analytics, Predictive Analytics","lastPublishedDoi":"10.21203/rs.3.rs-9515476/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9515476/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eUnderstanding and predicting consumer decision-making in digital environments remains a fundamental challenge, particularly in contexts characterized by limited and heterogeneous data. While advances in Machine Learning have enabled significant improvements in behavioral prediction, most existing approaches rely on large-scale datasets, limiting their applicability in real-world settings such as small and medium-sized enterprises (SMEs) and emerging markets. This study proposes a hybrid machine learning framework for predicting tourist decision making under data scarcity conditions in digital marketplaces. The framework integrates ensemble learning and neural modeling to capture both static and temporal behavioral patterns, while incorporating contextual and interaction-based features. Experimental evaluation was conducted using a real-world dataset of 10,000 user sessions collected from a tourism platform in Tanzania. To assess robustness, controlled experiments were performed under varying data availability scenarios. Results demonstrate that the proposed hybrid model consistently outperforms baseline models, achieving superior performance across multiple evaluation metrics, including accuracy, F1-score, and AUC-ROC. Notably, the model maintains strong predictive capability even when trained on reduced datasets, highlighting its robustness in data-constrained environments. Further more, interpretability analysis using Explainable AI reveals key behavioral and contextual factors influencing user decisions. The findings contribute to bridging the gap between advanced predictive analytics and real-world applicability by providing a scalable and adaptable framework for AI-driven decision modeling in low-data environments. The proposed approach has broad implications for digital marketplaces, particularly in emerging economies, where data limitations remain a critical barrier to the adoption of intelligent systems.\u003c/p\u003e","manuscriptTitle":"Predicting Tourist Decision-Making Under Data Scarcity: A Hybrid Machine Learning Framework for Digital Marketplaces","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-27 09:30:45","doi":"10.21203/rs.3.rs-9515476/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":"7e4b5737-94ea-41f5-9f8b-fb1e6ba9150e","owner":[],"postedDate":"April 27th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":66971911,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-04-28T21:30:59+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-27 09:30:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9515476","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9515476","identity":"rs-9515476","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}