Fairness-in-the-Workflow: How Machine Learning Practitioners at Big Tech Companies Approach Fairness in Recommender Systems
This research addresses the gap between academic fairness methods and practical implementation in high-stakes recommender systems for practitioners and stakeholders, but it is incremental as it builds on existing work without introducing new technical solutions.
The study mapped the workflow of machine learning practitioners at big tech companies to understand how they incorporate fairness into recommender systems, identifying challenges like defining fairness in multi-stakeholder contexts and organizational barriers such as time constraints and cross-team communication.
Recommender systems (RS), which are widely deployed across high-stakes domains, are susceptible to biases that can cause large-scale societal impacts. Researchers have proposed methods to measure and mitigate such biases -- but translating academic theory into practice is inherently challenging. RS practitioners must balance the competing interests of diverse stakeholders, including providers and users, and operate in dynamic environments. Through a semi-structured interview study (N=11), we map the RS practitioner workflow within large technology companies, focusing on how technical teams consider fairness internally and in collaboration with other (legal, data, and fairness) teams. We identify key challenges to incorporating fairness into existing RS workflows: defining fairness in RS contexts, particularly when navigating multi-stakeholder and dynamic fairness considerations. We also identify key organization-wide challenges: making time for fairness work and facilitating cross-team communication. Finally, we offer actionable recommendations for the RS community, including HCI researchers and practitioners.