Retargeting Customers Using Uplift Modeling

Todor Krastevich

Economic Studies journal, 2023, issue 2, 78-99

Abstract: “Traditional” digital marketing campaigns are based primarily on a priori geotargeting, augmented with profiling of potential consumers based on language, sociodemographics, interests and preferences. A step ahead is when experimental results from A/B testing are used for more precise retargeting, in order to prove in a statistically significant way the direction and size of the effect of a potential communication marketing impact. Through the application of uplift modelling, it is possible to complement the experimental data from A/B testing by identifying the effect of specific marketing treatments (e.g. a specific message, alternative display ad design, web page layout and/or change in price offer) on specific individuals as opposed to an overall increase or decrease in conversion rates caused by the impact. This technique can help evaluate and predict their responses through supervised machine-learning classification algorithms. This nuanced analysis allows for personalized targeting of marketing communication to only leads who are likely to respond positively to an impact. This paper proposes and demonstrates a prototype model for optimal retargeting of customers based on machine learning algorithms and open-source programming.

JEL-codes: C35 C55 C63 M37 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.iki.bas.bg/Journals/EconomicStudies/20 ... Todor-Krastevich.pdf

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:bas:econst:y:2023:i:2:p:78-99

Access Statistics for this article

More articles in Economic Studies journal from Bulgarian Academy of Sciences - Economic Research Institute Contact information at EDIRC.
Bibliographic data for series maintained by Diana Dimitrova ().