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

Susan Athey; Dean Karlan; Emil Palikot; Yuan Yuan

doi:10.3386/w30633

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

Susan Athey, Dean Karlan, Emil Palikot & Yuan Yuan

Working Paper 30633

DOI 10.3386/w30633

Issue Date November 2022

Revision Date March 2023

Online platforms often face the challenge of 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 the choices that online borrowers make when creating online profiles impact both of these objectives. We further support this finding 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 the impact of the feature on lender demand. We then evaluate counterfactual platform policies based on the changeable profile features, and identify approaches that can ameliorate the fairness-efficiency tension.

We thank Kiva Microfunds for generously sharing data and discussing the research questions. We thank Herman Donner and Kristine Koutout at Stanford Graduate School of Business and Allison Koenecke at Cornell University for comments and suggestions. The Golub Capital Social Impact Lab at Stanford Graduate School of Business provided funding for this research. This research has been subject to review and approval by Research Compliance Office at Stanford University, protocol number IRB-62442 and registered at AEA RCT registry with the number 0010030. The views expressed herein are those of the authors and do not necessarily reflect the views of the National Bureau of Economic Research.

Susan Athey
Susan Athey is currently on partial leave from Stanford University to serve in the U.S. Department of Justice. The research was substantively complete prior to the beginning of her government appointment, and the research does not reflect the views of the U.S. government or any other institution. She previously served on the boards of directors of Expedia (EXPE), Lending Club (LC), Rover (ROVR), Ripple, Turo, Innovations for Poverty Action, and CoinCenter, and also previously had a long term consulting relationship with Microsoft. She also previously advised venture capital firms X/Seed Capital and NYCA Partners, and previously worked on various consulting cases for a variety of clients through Keystone Strategy. She is the founding faculty director of the Golub Capital Social Impact Lab.
MARC RIS BibTeΧ
- randomized controlled trials registry entry
- November 4, 2022

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

Related

Topics

Programs

Working Groups

Projects

More from NBER