Smiles in Profiles: Improving Fairness and Efficiency Using Estimates of User Preferences in Online Marketplaces

Last registered on September 08, 2022

Pre-Trial

Trial Information

General Information

Title
Smiles in Profiles: Improving Fairness and Efficiency Using Estimates of User Preferences in Online Marketplaces
RCT ID
AEARCTR-0010030
Initial registration date
September 06, 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
September 08, 2022, 11:47 AM EDT

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

Locations

Region

Primary Investigator

Affiliation
Stanford University

Other Primary Investigator(s)

PI Affiliation
Stanford Graduate School of Business
PI Affiliation
Kellogg School of Management, Northwestern University
PI Affiliation
Carnegie Mellon University

Additional Trial Information

Status
Completed
Start date
2021-12-05
End date
2021-12-25
Secondary IDs
Prior work
This trial is based on or builds upon one or more prior RCTs.
Abstract
Online platforms often face challenges being both fair (i.e., non-discriminatory) and efficient (i.e., maximizing revenue). Using computer vision algorithms and observational data from a micro-lending marketplace, we find that choices made by borrowers creating online profiles impact both of these objectives. We further support this conclusion with a web-based randomized survey experiment. In the experiment, we create profile images using Generative Adversarial Networks that differ in a specific feature and estimate it's impact on lender demand. We then counterfactually evaluate alternative platform policies and identify particular approaches to influencing the changeable profile photo features that can ameliorate the fairness-efficiency tension.
External Link(s)

Registration Citation

Citation
Athey, Susan et al. 2022. "Smiles in Profiles: Improving Fairness and Efficiency Using Estimates of User Preferences in Online Marketplaces." AEA RCT Registry. September 08. https://doi.org/10.1257/rct.10030-1.0
Experimental Details

Interventions

Intervention(s)
In the intervention, subjects are shown six pairs of images generated using a computer vision algorithm and are asked to pick the preferred image in the pair. Images randomly vary by the gender of the person shown in the image, and whether the person smiles or not and the image is a body-shot or not.
Intervention Start Date
2021-12-05
Intervention End Date
2021-12-25

Primary Outcomes

Primary Outcomes (end points)
The primary outcome is whether the subject choose a profile or not.
Primary Outcomes (explanation)
We will use the data on subjects' choices to estimate the impact of gender, smile, and body-shot in determining the choice.

Secondary Outcomes

Secondary Outcomes (end points)
Secondary Outcomes (explanation)

Experimental Design

Experimental Design
Subjects recruited on Proflic.co receive one of fifteen predefined protocols. Protocols consists of six pairs of images in which gender of the person in the image and whether the person smiles or not and whether the image is a body-shot or not, is randomly assigned. All images are generated using a computer vision algorithm. Subjects are asked to choose one of the profiles in each pair. Thus, a treatment is a pair of images a subject is choosing from. Additionally, we include three attention checks; first, we ask for the reason people participate in microfinance; second, for the explanation of the choice decision, and third, for the occupation of the person shown in the previous slide.
Experimental Design Details
Randomization Method
Randomization is made by computer.
Randomization Unit
The unit of the randomization is an experimental session. Experimental sessions are choice instances in which a subject chooses between two profiles.
Was the treatment clustered?
No

Experiment Characteristics

Sample size: planned number of clusters
2460 experimental sessions
Sample size: planned number of observations
2460 experimental sessions
Sample size (or number of clusters) by treatment arms
A treatment arm is defined as a choice instance in which each profile varies in three binary dimensions. In result, we have 64 treatments each of the size 37.
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
IRB

Institutional Review Boards (IRBs)

IRB Name
Research Compliance Office
IRB Approval Date
2022-10-29
IRB Approval Number
62530

Post-Trial

Post Trial Information

Study Withdrawal

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

Request Information

Intervention

Is the intervention completed?
Yes
Intervention Completion Date
December 25, 2021, 12:00 +00:00
Data Collection Complete
Yes
Data Collection Completion Date
December 25, 2021, 12:00 +00:00
Final Sample Size: Number of Clusters (Unit of Randomization)
2460
Was attrition correlated with treatment status?
No
Final Sample Size: Total Number of Observations
2460
Final Sample Size (or Number of Clusters) by Treatment Arms
Data Publication

Data Publication

Is public data available?
No

Program Files

Program Files
No
Reports, Papers & Other Materials

Relevant Paper(s)

Reports & Other Materials