College and Major Choices with Personalized Recommendations

Last registered on June 06, 2022


Trial Information

General Information

College and Major Choices with Personalized Recommendations
Initial registration date
May 31, 2022

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
June 06, 2022, 5:17 AM EDT

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


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

Request Information

Primary Investigator

Stanford University

Other Primary Investigator(s)

PI Affiliation
Brown University

Additional Trial Information

In development
Start date
End date
Secondary IDs
Prior work
This trial does not extend or rely on any prior RCTs.
College and major choices are life-altering decisions with significant long-term labor market consequences. However, searching and learning about all available programs are extremely costly, and the application decisions are further complicated when the centralized matching mechanism is not strategy-proof. In this project, we conduct information interventions among high school students in China. We first survey the students about their preferences towards different types of colleges and major categories and measure their risk preferences, which enables us to provide personalized information intervention. In the randomized trial, we recommend college-major programs based on the treated students’ revealed preferences, so that they become better informed about the availability of suitable programs without the costly search. In addition, we tailor our recommendations by incorporating the predicted probability of admission to each of the programs, improving the sophistication of the students’ rank-order lists. The effectiveness of the personalized recommendation is evaluated based on students’ submitted rank-order lists, actual admission results, and their levels of satisfaction. We also explore the general equilibrium effects by conducting a simulation analysis assuming the personalized recommendation is available to all students.
External Link(s)

Registration Citation

Qiu, Xinyao and Xiaoyang Ye. 2022. "College and Major Choices with Personalized Recommendations." AEA RCT Registry. June 06.
Experimental Details


Intervention Start Date
Intervention End Date

Primary Outcomes

Primary Outcomes (end points)
Students' submitted rank-order lists, admission results, as well as their levels of satisfaction with the application process and admission results.
Primary Outcomes (explanation)

Secondary Outcomes

Secondary Outcomes (end points)
Secondary Outcomes (explanation)

Experimental Design

Experimental Design
Students who sign up for the experiment are randomly assigned to the control group and the treatment group. We provide the treated students with a list of personalized college-major programs based on their college entrance exam performances, preferences for colleges and majors, and risk preferences. After the college application process, we collect their submitted rank-order list, admission results, and their levels of satisfaction. We examine how they respond to the personalized recommendations, and whether the treatment improves admission outcomes, both objectively and subjectively.

Experimental Design Details
Not available
Randomization Method
Randomization is done by a computer.
Randomization Unit
Was the treatment clustered?

Experiment Characteristics

Sample size: planned number of clusters
Roughly 10 high schools.
Sample size: planned number of observations
Roughly 800 students.
Sample size (or number of clusters) by treatment arms
400 students in the control group, and 400 students in the treatment group.
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)

Institutional Review Boards (IRBs)

IRB Name
IRB Approval Date
IRB Approval Number