Dynamic Fairness

Dynamic Fairness is a fairness metric in machine learning that, as a temporal adaptation of static fairness criteria, accounts for evolving relationships between sensitive attributes and outcomes over time to ensure equitable model behavior across sequential decision-making contexts.

7

Publications

126

Citations

18

Authors

11

Institutions

Publications per year

2017–2026

4

Authors

18

  1. ST
    Stefan T. Trautmann

    Tilburg University, Netherlands

    1 publications · 33 citations

    1

    h-index

  2. LA
    Lutfa Akter

    Bangladesh University of Engineering and Technology, Bangladesh

    1 publications · 17 citations

    1

    h-index

  3. NS
    Niya Stoimenova

    University of Cologne, Germany

    1 publications · 14 citations

    1

    h-index

  4. MW
    Min Wen

    University of Pennsylvania, United States

    1 publications · 12 citations

    1

    h-index

  5. KM
    Kaushik Mallik

    Max Planck Institute for Software Systems, Germany

    1 publications · 17 citations

    1

    h-index

1–5 of 18

Venues

  1. Journal of Business and Psychology

    1 publications · 23 citations

    1

    h-index

  2. arXiv (Cornell University)

    Repository · 1 publications · 12 citations

    1

    h-index

  3. Economics Letters

    1 publications · 33 citations

    1

    h-index

  4. ACM Transactions on Information Systems

    1 publications · 10 citations

    1

    h-index

  5. AI & Society

    1 publications · 14 citations

    1

    h-index

1–5