A machine learning decision tree model to predict consumer purchase behaviour: a microeconomic view from online social platforms in Iran

Pejman Ebrahimi, Mohammad Naeim Hassani, Seyed Mohammad Khansari, Aidin Salamzadeh and Maria Fekete-Farkas

International Journal of Business and Globalisation, 2025, vol. 40, issue 4, 289-302

Abstract: This study proposes a map to predict consumer purchase behaviour using a decision tree algorithm using machine learning. Python programming language (Jupyter and Visual Studio Code IDEs) is used accordingly. The study's statistical population involved Iranian online social platform users who made at least one online purchase. Instagram, Facebook, Telegram, YouTube, and WhatsApp platforms were used for data gathering. According to the map results presented based on data of demographic variables of 376 respondents, Instagram is the most popular platform in Iran with a high difference in terms of advertising and online shopping. It has more popularity in almost all age and education groups; however, other platforms also have their users according to their demographic attributes. The proposed model is also practically capable of prediction with an accuracy of >96%. This research contributes to the extant literature by using machine learning and its practical libraries to predict consumer behaviour.

Keywords: media brand; co-creation; value proposition; customer loyalty; social media. (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=147956 (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:ids:ijbglo:v:40:y:2025:i:4:p:289-302

Access Statistics for this article

More articles in International Journal of Business and Globalisation from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().