mlsanityData to 14 Oct 2026

Fairness-in-the-Workflow: How Machine Learning Practitioners at Big Tech Companies Approach Fairness in Recommender Systems

arXiv 2505.19441 ↗First posted 26 May 2025cs.HC cs.AI cs.CYcited by 0

Not on the map. Why?

Abstract (arXiv)

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. 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 legal, data, and fairness teams. We identify key challenges to incorporating fairness into existing RS workflows: defining fairness in RS contexts, balancing multi-stakeholder interests, and navigating dynamic environments. 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 practitioners and HCI researchers.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 79 of its 164 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

79 of 164 references.

References · 79

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  2. 2018Datasheets for Datasetscited by 1,386
  3. 2018Model Cards for Model Reportingcited by 1,080
  4. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  5. 2014Certifying and removing disparate impactcited by 715
  6. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
  7. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 586
  8. 2017On Fairness and Calibrationcited by 406
  9. 2017Algorithmic decision making and the cost of fairnesscited by 403
  10. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 369
  11. 2019Measurement and Fairnesscited by 308
  12. 2018Improving fairness in machine learning systems: What do industry practitioners need?cited by 262
38 more
  1. 2020Bias and Debias in Recommender System: A Survey and Future Directionscited by 240
  2. 2018A comparative study of fairness-enhancing interventions in machine learningcited by 208
  3. 2017Avoiding Discrimination through Causal Reasoningcited by 194
  4. 2019A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cyclecited by 193
  5. 2018Fairness of Exposure in Rankingscited by 190
  6. 2019Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Searchcited by 138
  7. 2019Fairness in Recommendation Ranking through Pairwise Comparisonscited by 127
  8. 2018Equity of Attention: Amortizing Individual Fairness in Rankingscited by 124
  9. 2017FA*IR: A Fair Top-k Ranking Algorithmcited by 113
  10. 201850 Years of Test (Un)fairness: Lessons for Machine Learningcited by 101
  11. 2018The Measure and Mismeasure of Fairnesscited by 95
  12. 2013Discrimination in Online Ad Deliverycited by 93
  13. 2019Problem Formulation and Fairnesscited by 85
  14. 2019Managing Popularity Bias in Recommender Systems with Personalized Re-rankingcited by 82
  15. 2016Measuring Fairness in Ranked Outputscited by 81
  16. 2018An Empirical Study of Rich Subgroup Fairness for Machine Learningcited by 81
  17. 2021User-oriented Fairness in Recommendationcited by 75
  18. 2017Multisided Fairness for Recommendationcited by 70
  19. 2019Putting Fairness Principles into Practice: Challenges, Metrics, and Improvementscited by 70
  20. 2018Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Makingcited by 67
  21. 2021Assessing the Fairness of AI Systems: AI Practitioners' Processes, Challenges, and Needs for Supportcited by 63
  22. 2022Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluationcited by 59
  23. 2020Evaluating Stochastic Rankings with Expected Exposurecited by 53
  24. 2023Who Audits the Auditors? Recommendations from a field scan of the algorithmic auditing ecosystemcited by 52
  25. 2019Average Individual Fairness: Algorithms, Generalization and Experimentscited by 46
  26. 2017Designing Fair Ranking Schemescited by 40
  27. 2020Where Responsible AI meets Reality: Practitioner Perspectives on Enablers for shifting Organizational Practicescited by 39
  28. 2021Algorithmic Amplification of Politics on Twittercited by 38
  29. 2022Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkitscited by 34
  30. 2018Reducing Disparate Exposure in Ranking: A Learning To Rank Approachcited by 33
  31. 2022Understanding Practices, Challenges, and Opportunities for User-Engaged Algorithm Auditing in Industry Practicecited by 32
  32. 2024Towards AI Accountability Infrastructure: Gaps and Opportunities in AI Audit Toolingcited by 29
  33. 2022Seeing Like a Toolkit: How Toolkits Envision the Work of AI Ethicscited by 28
  34. 2022Understanding Machine Learning Practitioners' Data Documentation Perceptions, Needs, Challenges, and Desideratacited by 28
  35. 2022Building Human Values into Recommender Systems: An Interdisciplinary Synthesiscited by 22
  36. 2024The Impossibility of Fair LLMscited by 22
  37. 2018User Fairness in Recommender Systemscited by 21
  38. 2022Fair ranking: a critical review, challenges, and future directionscited by 21

50 most cited of 79 All 79 (JSON)

Built on by

Not cited yet.