Modelling users’ intention to migrate from free to premium personal cloud storage in freemium business models: A machine learning approach

John Oredo

African Journal of Science, Technology, Innovation and Development, 2025, vol. 17, issue 6, 845-868

Abstract: Extant technology post-adoption studies focus on effective and continued use. The current study models the features that explain and predict users’ intention to migrate from free to premium cloud storage services. Data were collected from 122 postgraduate students on perceived ease of use, perceived usefulness, perceived risk, perceived trust, IT mindfulness and perceived familiarity. CRISP-DM framework for machine learning was used to conceptualize the study. Perceived usefulness, perceived satisfaction, and IT mindfulness had positive effects on the intention to migrate while perceived risk and perceived trust had negative effects. Model’s F1 score indicated its ability to accurately identify users who were likely to migrate 64 percent of the time. AUC was 0.61, indicating model’s good discriminative power. Study extends technology post adoption theories by incorporating IT Mindfulness. Explaining and predicting users’ intention to migrate using ML affirms its relevance in theory building and confirmation. Additionally, the study informs practitioners and users’ technology post adoption behaviour.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/20421338.2025.2545112 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:rajsxx:v:17:y:2025:i:6:p:845-868

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/rajs20

DOI: 10.1080/20421338.2025.2545112

Access Statistics for this article

African Journal of Science, Technology, Innovation and Development is currently edited by None

More articles in African Journal of Science, Technology, Innovation and Development from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().