Designing fair ranking schemes

Abolfazl Asudeh, H. V. Jagadish, Julia Stoyanovich, Gautam Das

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Items from a database are often ranked based on a combination of criteria. The weight given to each criterion in the combination can greatly affect the fairness of the produced ranking, for example, preferring men over women. A user may have the flexibility to choose combinations that weigh these criteria differently, within limits. In this paper, we develop a system that helps users choose criterion weights that lead to greater fairness. We consider ranking functions that compute the score of each item as a weighted sum of (numeric) attribute values, and then sort items on their score. Each ranking function can be expressed as a point in a multidimensional space. For a broad range of fairness criteria, including proportionality, we show how to efficiently identify regions in this space that satisfy these criteria. Using this identification method, our system is able to tell users whether their proposed ranking function satisfies the desired fairness criteria and, if it does not, to suggest the smallest modification that does. Our extensive experiments on real datasets demonstrate that our methods are able to find solutions that satisfy fairness criteria effectively (usually with only small changes to proposed weight vectors) and efficiently (in interactive time, after some initial pre-processing).

    Original languageEnglish (US)
    Title of host publicationSIGMOD 2019 - Proceedings of the 2019 International Conference on Management of Data
    PublisherAssociation for Computing Machinery
    Pages1259-1276
    Number of pages18
    ISBN (Electronic)9781450356435
    StatePublished - Jun 25 2019
    Event2019 International Conference on Management of Data, SIGMOD 2019 - Amsterdam, Netherlands
    Duration: Jun 30 2019Jul 5 2019

    Publication series

    NameProceedings of the ACM SIGMOD International Conference on Management of Data
    ISSN (Print)0730-8078

    Conference

    Conference2019 International Conference on Management of Data, SIGMOD 2019
    CountryNetherlands
    CityAmsterdam
    Period6/30/197/5/19

    Fingerprint

    Processing
    Experiments

    Keywords

    • Data Ethics
    • Fairness
    • Responsible Data Management

    ASJC Scopus subject areas

    • Software
    • Information Systems

    Cite this

    Asudeh, A., Jagadish, H. V., Stoyanovich, J., & Das, G. (2019). Designing fair ranking schemes. In SIGMOD 2019 - Proceedings of the 2019 International Conference on Management of Data (pp. 1259-1276). (Proceedings of the ACM SIGMOD International Conference on Management of Data). Association for Computing Machinery.

    Designing fair ranking schemes. / Asudeh, Abolfazl; Jagadish, H. V.; Stoyanovich, Julia; Das, Gautam.

    SIGMOD 2019 - Proceedings of the 2019 International Conference on Management of Data. Association for Computing Machinery, 2019. p. 1259-1276 (Proceedings of the ACM SIGMOD International Conference on Management of Data).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Asudeh, A, Jagadish, HV, Stoyanovich, J & Das, G 2019, Designing fair ranking schemes. in SIGMOD 2019 - Proceedings of the 2019 International Conference on Management of Data. Proceedings of the ACM SIGMOD International Conference on Management of Data, Association for Computing Machinery, pp. 1259-1276, 2019 International Conference on Management of Data, SIGMOD 2019, Amsterdam, Netherlands, 6/30/19.
    Asudeh A, Jagadish HV, Stoyanovich J, Das G. Designing fair ranking schemes. In SIGMOD 2019 - Proceedings of the 2019 International Conference on Management of Data. Association for Computing Machinery. 2019. p. 1259-1276. (Proceedings of the ACM SIGMOD International Conference on Management of Data).
    Asudeh, Abolfazl ; Jagadish, H. V. ; Stoyanovich, Julia ; Das, Gautam. / Designing fair ranking schemes. SIGMOD 2019 - Proceedings of the 2019 International Conference on Management of Data. Association for Computing Machinery, 2019. pp. 1259-1276 (Proceedings of the ACM SIGMOD International Conference on Management of Data).
    @inproceedings{d058a73da1b3428c80f77762424d1e90,
    title = "Designing fair ranking schemes",
    abstract = "Items from a database are often ranked based on a combination of criteria. The weight given to each criterion in the combination can greatly affect the fairness of the produced ranking, for example, preferring men over women. A user may have the flexibility to choose combinations that weigh these criteria differently, within limits. In this paper, we develop a system that helps users choose criterion weights that lead to greater fairness. We consider ranking functions that compute the score of each item as a weighted sum of (numeric) attribute values, and then sort items on their score. Each ranking function can be expressed as a point in a multidimensional space. For a broad range of fairness criteria, including proportionality, we show how to efficiently identify regions in this space that satisfy these criteria. Using this identification method, our system is able to tell users whether their proposed ranking function satisfies the desired fairness criteria and, if it does not, to suggest the smallest modification that does. Our extensive experiments on real datasets demonstrate that our methods are able to find solutions that satisfy fairness criteria effectively (usually with only small changes to proposed weight vectors) and efficiently (in interactive time, after some initial pre-processing).",
    keywords = "Data Ethics, Fairness, Responsible Data Management",
    author = "Abolfazl Asudeh and Jagadish, {H. V.} and Julia Stoyanovich and Gautam Das",
    year = "2019",
    month = "6",
    day = "25",
    language = "English (US)",
    series = "Proceedings of the ACM SIGMOD International Conference on Management of Data",
    publisher = "Association for Computing Machinery",
    pages = "1259--1276",
    booktitle = "SIGMOD 2019 - Proceedings of the 2019 International Conference on Management of Data",

    }

    TY - GEN

    T1 - Designing fair ranking schemes

    AU - Asudeh, Abolfazl

    AU - Jagadish, H. V.

    AU - Stoyanovich, Julia

    AU - Das, Gautam

    PY - 2019/6/25

    Y1 - 2019/6/25

    N2 - Items from a database are often ranked based on a combination of criteria. The weight given to each criterion in the combination can greatly affect the fairness of the produced ranking, for example, preferring men over women. A user may have the flexibility to choose combinations that weigh these criteria differently, within limits. In this paper, we develop a system that helps users choose criterion weights that lead to greater fairness. We consider ranking functions that compute the score of each item as a weighted sum of (numeric) attribute values, and then sort items on their score. Each ranking function can be expressed as a point in a multidimensional space. For a broad range of fairness criteria, including proportionality, we show how to efficiently identify regions in this space that satisfy these criteria. Using this identification method, our system is able to tell users whether their proposed ranking function satisfies the desired fairness criteria and, if it does not, to suggest the smallest modification that does. Our extensive experiments on real datasets demonstrate that our methods are able to find solutions that satisfy fairness criteria effectively (usually with only small changes to proposed weight vectors) and efficiently (in interactive time, after some initial pre-processing).

    AB - Items from a database are often ranked based on a combination of criteria. The weight given to each criterion in the combination can greatly affect the fairness of the produced ranking, for example, preferring men over women. A user may have the flexibility to choose combinations that weigh these criteria differently, within limits. In this paper, we develop a system that helps users choose criterion weights that lead to greater fairness. We consider ranking functions that compute the score of each item as a weighted sum of (numeric) attribute values, and then sort items on their score. Each ranking function can be expressed as a point in a multidimensional space. For a broad range of fairness criteria, including proportionality, we show how to efficiently identify regions in this space that satisfy these criteria. Using this identification method, our system is able to tell users whether their proposed ranking function satisfies the desired fairness criteria and, if it does not, to suggest the smallest modification that does. Our extensive experiments on real datasets demonstrate that our methods are able to find solutions that satisfy fairness criteria effectively (usually with only small changes to proposed weight vectors) and efficiently (in interactive time, after some initial pre-processing).

    KW - Data Ethics

    KW - Fairness

    KW - Responsible Data Management

    UR - http://www.scopus.com/inward/record.url?scp=85061747789&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85061747789&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:85061747789

    T3 - Proceedings of the ACM SIGMOD International Conference on Management of Data

    SP - 1259

    EP - 1276

    BT - SIGMOD 2019 - Proceedings of the 2019 International Conference on Management of Data

    PB - Association for Computing Machinery

    ER -