Unlocking high-value users with machine learning: Enhancing personalisation and return on marketing investment with iBQML

Brianna Mersey
Additional contact information
Brianna Mersey: Monks, Canada

Applied Marketing Analytics: The Peer-Reviewed Journal, 2025, vol. 11, issue 1, 12-22

Abstract: In today’s competitive landscape, poor audience targeting can drain resources, diminish campaign performance and erode customer trust. Brands that fail to deliver personalised, timely experiences risk low engagement and missed growth opportunities. To succeed, marketers must activate first-party data to deliver tailored messaging aligned with users’ real-time behaviours and preferences. Instant BigQuery Machine Learning (iBQML) provides a powerful, accessible way to operationalise machine learning on firstparty Google Analytics 4 data. It enables brands to run propensity models that predict the likelihood of high-value customer actions — helping refine targeting strategies, increase conversion efficiency and deepen customer relationships. By focusing on high-potential segments, brands can improve return on advertising spend, optimise conversion rates and foster long-term loyalty through personalised remarketing campaigns. As a lightweight alternative to more complex platforms like Vertex AI or DataRobot, iBQML is ideal for organisations looking to quickly adopt machine learning without deep technical investment. Nevertheless, it comes with limitations — such as a narrow range of model types, a lack of parameter tuning, and potentially high costs at scale — that should be carefully considered before long-term implementation. This paper discusses how iBQML can help businesses to stay competitive in an increasingly data-driven world. This article is also included in The Business & Management Collection which can be accessed at https://hstalks.com/ business/.

Keywords: audience segmentation; iBQML; GA4; machine learning; propensity modelling; personalisation; first-party data (search for similar items in EconPapers)
JEL-codes: M3 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://hstalks.com/article/9567/download/ (application/pdf)
https://hstalks.com/article/9567/ (text/html)
Requires a paid subscription for full access.

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:aza:ama000:y:2025:v:11:i:1:p:12-22

Access Statistics for this article

More articles in Applied Marketing Analytics: The Peer-Reviewed Journal from Henry Stewart Publications
Bibliographic data for series maintained by Henry Stewart Talks ().