A developer-oriented recommender model for the app store: A predictive network analytics approach

Basit Öğe Kaydı
dc.authoridDelen, Dursun/0000-0001-8857-5148
dc.authorwosidDelen, Dursun/AGA-9892-2022
dc.contributor.authorDavazdahemami, Behrooz
dc.contributor.authorKalgotra, Pankush
dc.contributor.authorZolbanin, Hamed M.
dc.contributor.authorDelen, Dursun
dc.date.accessioned2024-05-19T14:45:50Z
dc.date.available2024-05-19T14:45:50Z
dc.date.issued2023
dc.departmentİstinye Üniversitesien_US
dc.description.abstractWhile thousands of new mobile applications (i.e., apps) are being added to the major app markets daily, only a small portion of them attain their financial goals and survive in these competitive marketplaces. A key to the quick growth and success of relatively less popular apps is that they should make their way to the limited list of apps recommended to users of already popular apps; however, the focus of the current literature on consumers has created a void of design principles for app developers. In this study, employing a predictive network analytics approach combined with deep learning-based natural language processing and explainable artificial intelligence techniques, we shift the focus from consumers and propose a developer-oriented recommender model. We employ a set of app-specific and network-driven variables to present a novel approach for predicting potential recommendation relationships among apps, which enables app developers and marketers to characterize and target appropriate consumers. We validate the proposed model using a large (>23,000), longitudinal dataset of medical apps collected from the iOS App Store at two time points. From a total of 10,234 network links (rec-ommendations) formed between the two data collection points, the proposed approach was able to correctly predict 8,780 links (i.e., 85.8 %). We perform Shapley Additive exPlanation (SHAP) analysis to identify the most important determinants of link formations and provide insights for the app developers about the factors and design principles they can incorporate into their development process to maximize the chances of success for their apps.en_US
dc.identifier.doi10.1016/j.jbusres.2023.113649
dc.identifier.issn0148-2963
dc.identifier.issn1873-7978
dc.identifier.scopus2-s2.0-85147111531en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org10.1016/j.jbusres.2023.113649
dc.identifier.urihttps://hdl.handle.net/20.500.12713/5366
dc.identifier.volume158en_US
dc.identifier.wosWOS:000978776000001en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherElsevier Science Incen_US
dc.relation.ispartofJournal of Business Researchen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz20240519_kaen_US
dc.subjectMobile Applicationen_US
dc.subjectRecommender Modelen_US
dc.subjectNetwork Analyticsen_US
dc.subjectPredictive Analyticsen_US
dc.subjectExplainable Aien_US
dc.titleA developer-oriented recommender model for the app store: A predictive network analytics approachen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu