Fairness through Experimentation: Inequality in A/B testing as an approach to responsible design
Guillaume Saint-Jacques, Amir Sepehri, Nicole Li, Igor Perisic

TL;DR
This paper introduces a novel experimentation-based approach to fairness in product design by measuring inequality impacts using the Atkinson index in A/B testing, promoting responsible and inclusive innovation.
Contribution
It presents a new method to assess fairness through inequality measurement in A/B testing, including causal inference and site-wide impact analysis, with real-world applications and scalable implementation.
Findings
Identified areas where product innovations foster fairness
Developed scalable tools for inequality measurement in experiments
Deployed method at scale with thousands of experiments
Abstract
As technology continues to advance, there is increasing concern about individuals being left behind. Many businesses are striving to adopt responsible design practices and avoid any unintended consequences of their products and services, ranging from privacy vulnerabilities to algorithmic bias. We propose a novel approach to fairness and inclusiveness based on experimentation. We use experimentation because we want to assess not only the intrinsic properties of products and algorithms but also their impact on people. We do this by introducing an inequality approach to A/B testing, leveraging the Atkinson index from the economics literature. We show how to perform causal inference over this inequality measure. We also introduce the concept of site-wide inequality impact, which captures the inclusiveness impact of targeting specific subpopulations for experiments, and show how to conduct…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsExperimental Behavioral Economics Studies · Ethics and Social Impacts of AI · Economic and Environmental Valuation
