Effect of AI Generated Personalized Thumbnails on Platforms

How to cite

JIA, Jinghao. 2025. "Effect of AI Generated Personalized Thumbnails on Platforms." AEA RCT Registry. AEARCTR-0015396. https://doi.org/10.1257/rct.15396-1.0

Download: BibTeX · RIS — for reference managers without a browser translator. Zotero and most others pick up this page's citation metadata directly.

Jinghao JIA*

* Primary investigator

Registry ID
AEARCTR-0015396
DOI
https://doi.org/10.1257/rct.15396-1.0
First registered
Last updated
Status
In development
Trial dates
2025-02-18 – 2025-07-01
Countries
Private
Registry record
http://www.socialscienceregistry.org/trials/15396

Abstract

In the evolving landscape of e-commerce, we recognize the critical role of personalized marketing strategies in enhancing user engagement and influencing purchasing decisions. While much research has focused on optimizing recommendation algorithms, the impact of personalized visual elements, such as customized product covers, remains underexplored. To address this gap, we investigate how personalized product covers interact with recommendation systems to shape consumer behavior. We developed a simulated online shopping platform that replicates real-world e-commerce environments, incorporating product displays with quantified visual attributes. Using advanced analysis tools, we design personalized covers tailored to individual user preferences, ensuring both experimental control and realism. Our study follows a 2×2 factorial design to examine the effects of personalized covers and recommendation systems on engagement, purchase intent, and user satisfaction. Beyond practical implications, we contribute to theoretical discussions on consumer decision-making, exploring whether visual personalization influences emotional responses, decision confidence, and product exploration. By integrating insights from consumer behavior and digital marketing, we aim to provide both academic and industry perspectives on the role of visual elements in e-commerce. Our findings will help businesses refine their strategies, enhance user experiences, and optimize recommendation mechanisms for greater inclusivity and effectiveness.

Experimental design

Our experiment employs a factorial design to examine the interaction between visual personalization and recommendation systems in shaping consumer behavior. Participants engage with a simulated e-commerce platform that mimics real shopping environments, where different levels of personalization are applied to product displays and recommendations. By systematically varying these factors, we assess their effects on user engagement, decision-making, and purchasing behavior. This approach allows us to explore how personalized visual elements influence consumer preferences and whether they complement or modify the impact of algorithmic recommendations in digital marketplaces.

Design details

Randomization method
computer-generated algorithm
Randomization unit
individual, group level randomization for some treatment
Clusters
10 schools
Observations
300
Arms
75 participants control 75 participants for thumbnail treatment only 75 participants for recommendation treatment only 75 for both treatment
Primary outcomes
Purchasing decision

Cited by

No citation data available for this registration yet.

Keywords