Effect of AI Generated Personalized Thumbnails on Platforms

Last registered on February 20, 2025

Pre-Trial

Trial Information

General Information

Title
Effect of AI Generated Personalized Thumbnails on Platforms
RCT ID
AEARCTR-0015396
Initial registration date
February 16, 2025

Initial registration date is when the trial was registered.

It corresponds to when the registration was submitted to the Registry to be reviewed for publication.

First published
February 20, 2025, 5:21 AM EST

First published corresponds to when the trial was first made public on the Registry after being reviewed.

Locations

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information

Primary Investigator

Affiliation
The Hong Kong University of Science and Technology (Guangzhou)

Other Primary Investigator(s)

Additional Trial Information

Status
In development
Start date
2025-02-18
End date
2025-07-01
Secondary IDs
Prior work
This trial does not extend or rely on any prior RCTs.
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.
External Link(s)

Registration Citation

Citation
JIA, Jinghao. 2025. "Effect of AI Generated Personalized Thumbnails on Platforms." AEA RCT Registry. February 20. https://doi.org/10.1257/rct.15396-1.0
Experimental Details

Interventions

Intervention(s)
Intervention Start Date
2025-04-01
Intervention End Date
2025-06-01

Primary Outcomes

Primary Outcomes (end points)
Purchasing decision
Primary Outcomes (explanation)

Secondary Outcomes

Secondary Outcomes (end points)
Secondary Outcomes (explanation)

Experimental Design

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.
Experimental Design Details
Not available
Randomization Method
computer-generated algorithm
Randomization Unit
individual, group level randomization for some treatment
Was the treatment clustered?
No

Experiment Characteristics

Sample size: planned number of clusters
10 schools
Sample size: planned number of observations
300
Sample size (or number of clusters) by treatment arms
75 participants control
75 participants for thumbnail treatment only
75 participants for recommendation treatment only
75 for both treatment
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
IRB

Institutional Review Boards (IRBs)

IRB Name
RESEARCH CONSTRUCTION AND DEVELOPMENT DEPARTMENT, THE HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGY (GUANGZHOU)
IRB Approval Date
2024-10-22
IRB Approval Number
HKUST(GZ)-HSP-2024-0070