Bias Mitigation

Bias Mitigation is a methodological intervention within the field of algorithmic fairness that systematically identifies, reduces, or corrects discriminatory patterns in automated decision-making processes arising from biased data, models, or assumptions, thereby distinguishing it from general fairness-aware techniques by its targeted focus on the sources and effects of bias in domains such as credit scoring, risk assessment, recommendation systems, and ethical data use.

535

Publications

42.9K

Citations

1.6K

Authors

611

Institutions

Publications per year

2017–2026

461

Authors

1.6K

  1. KR
    Kush R. Varshney

    IBM Research - Thomas J. Watson Research Center, United States

    8 publications · 1.7K citations

    8

    h-index

  2. FS
    Federica Sarro

    University College London, United Kingdom

    7 publications · 420 citations

    7

    h-index

  3. SB
    Solon Barocas

    Cornell University, United States

    7 publications · 4.2K citations

    7

    h-index

  4. EF
    Emilio Ferrara

    University of Southern California, United States

    6 publications · 1.1K citations

    6

    h-index

  5. KN
    Karthikeyan Natesan Ramamurthy

    Arizona State University, United States

    6 publications · 1.5K citations

    6

    h-index

1–5 of 1.6K

Venues

  1. arXiv (Cornell University)

    Repository · 69 publications · 2.9K citations

    26

    h-index

  2. SSRN Electronic Journal

    Repository · 20 publications · 3K citations

    17

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 11 publications · 199 citations

    10

    h-index

  4. Information Systems Research

    ISR · 4 publications · 292 citations

    4

    h-index

  5. IEEE Transactions on Visualization and Computer Graphics

    TVCG · 4 publications · 148 citations

    4

    h-index

1–5