Unveiling systematic biases in decisional processes: an application to discrimination discovery

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

1 Citaat (Scopus)

Uittreksel

Decisional processes are at the basis of several security and privacy applications. However, they are often not transparent and can be affected by human or algorithmic biases that may lead to systematically misleading or unfair outcomes. To unveil these biases, one has to identify which information was used to make the decision and to quantify to what extent such information has influenced the process outcome. Two classes of techniques are widely used to determine possible correlation between variables within decisional processes from observational data: (i) econometric techniques, in particular regression analysis, and (ii) knowledge discovery techniques, in particular association rules mining. However, these techniques, taken individually, have intrinsic drawbacks that limit their applicability. In thiswork, we propose an approach for unveiling biases in decisional processes, which leverages association rule mining for systematic hypothesis generation and regression analysis for model selection and recommendation extraction. We demonstrate the proposed approach in the context of discrimination detection, showing that not only it provides 'statistically significant' evidence of discrimination but it also allows for a more efficient operationalization of the recommendations extracted, upon which the decision maker can operate.

TaalEngels
TitelAsiaCCS 2019 - Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security
Plaats van productieNew York
UitgeverijAssociation for Computing Machinery, Inc
Pagina's67-72
Aantal pagina's6
ISBN van elektronische versie978-1-4503-6752-3
DOI's
StatusGepubliceerd - 2 jul 2019
Evenement2019 ACM Asia Conference on Computer and Communications Security, AsiaCCS 2019 - Auckland, Nieuw-Zeeland
Duur: 9 jul 201912 jul 2019

Congres

Congres2019 ACM Asia Conference on Computer and Communications Security, AsiaCCS 2019
LandNieuw-Zeeland
StadAuckland
Periode9/07/1912/07/19

Vingerafdruk

Association rules
Regression analysis
Data mining

Trefwoorden

    Citeer dit

    Genga, L., Allodi, L., & Zannone, N. (2019). Unveiling systematic biases in decisional processes: an application to discrimination discovery. In AsiaCCS 2019 - Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security (blz. 67-72). New York: Association for Computing Machinery, Inc. DOI: 10.1145/3321705.3329856
    Genga, Laura ; Allodi, Luca ; Zannone, Nicola. / Unveiling systematic biases in decisional processes : an application to discrimination discovery. AsiaCCS 2019 - Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security. New York : Association for Computing Machinery, Inc, 2019. blz. 67-72
    @inproceedings{90a69bf9df4d49e9b8673e668b31610b,
    title = "Unveiling systematic biases in decisional processes: an application to discrimination discovery",
    abstract = "Decisional processes are at the basis of several security and privacy applications. However, they are often not transparent and can be affected by human or algorithmic biases that may lead to systematically misleading or unfair outcomes. To unveil these biases, one has to identify which information was used to make the decision and to quantify to what extent such information has influenced the process outcome. Two classes of techniques are widely used to determine possible correlation between variables within decisional processes from observational data: (i) econometric techniques, in particular regression analysis, and (ii) knowledge discovery techniques, in particular association rules mining. However, these techniques, taken individually, have intrinsic drawbacks that limit their applicability. In thiswork, we propose an approach for unveiling biases in decisional processes, which leverages association rule mining for systematic hypothesis generation and regression analysis for model selection and recommendation extraction. We demonstrate the proposed approach in the context of discrimination detection, showing that not only it provides 'statistically significant' evidence of discrimination but it also allows for a more efficient operationalization of the recommendations extracted, upon which the decision maker can operate.",
    keywords = "Association Rule Mining, Decisional Process, Econometrics",
    author = "Laura Genga and Luca Allodi and Nicola Zannone",
    year = "2019",
    month = "7",
    day = "2",
    doi = "10.1145/3321705.3329856",
    language = "English",
    pages = "67--72",
    booktitle = "AsiaCCS 2019 - Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security",
    publisher = "Association for Computing Machinery, Inc",
    address = "United States",

    }

    Genga, L, Allodi, L & Zannone, N 2019, Unveiling systematic biases in decisional processes: an application to discrimination discovery. in AsiaCCS 2019 - Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security. Association for Computing Machinery, Inc, New York, blz. 67-72, Auckland, Nieuw-Zeeland, 9/07/19. DOI: 10.1145/3321705.3329856

    Unveiling systematic biases in decisional processes : an application to discrimination discovery. / Genga, Laura; Allodi, Luca; Zannone, Nicola.

    AsiaCCS 2019 - Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security. New York : Association for Computing Machinery, Inc, 2019. blz. 67-72.

    Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

    TY - GEN

    T1 - Unveiling systematic biases in decisional processes

    T2 - an application to discrimination discovery

    AU - Genga,Laura

    AU - Allodi,Luca

    AU - Zannone,Nicola

    PY - 2019/7/2

    Y1 - 2019/7/2

    N2 - Decisional processes are at the basis of several security and privacy applications. However, they are often not transparent and can be affected by human or algorithmic biases that may lead to systematically misleading or unfair outcomes. To unveil these biases, one has to identify which information was used to make the decision and to quantify to what extent such information has influenced the process outcome. Two classes of techniques are widely used to determine possible correlation between variables within decisional processes from observational data: (i) econometric techniques, in particular regression analysis, and (ii) knowledge discovery techniques, in particular association rules mining. However, these techniques, taken individually, have intrinsic drawbacks that limit their applicability. In thiswork, we propose an approach for unveiling biases in decisional processes, which leverages association rule mining for systematic hypothesis generation and regression analysis for model selection and recommendation extraction. We demonstrate the proposed approach in the context of discrimination detection, showing that not only it provides 'statistically significant' evidence of discrimination but it also allows for a more efficient operationalization of the recommendations extracted, upon which the decision maker can operate.

    AB - Decisional processes are at the basis of several security and privacy applications. However, they are often not transparent and can be affected by human or algorithmic biases that may lead to systematically misleading or unfair outcomes. To unveil these biases, one has to identify which information was used to make the decision and to quantify to what extent such information has influenced the process outcome. Two classes of techniques are widely used to determine possible correlation between variables within decisional processes from observational data: (i) econometric techniques, in particular regression analysis, and (ii) knowledge discovery techniques, in particular association rules mining. However, these techniques, taken individually, have intrinsic drawbacks that limit their applicability. In thiswork, we propose an approach for unveiling biases in decisional processes, which leverages association rule mining for systematic hypothesis generation and regression analysis for model selection and recommendation extraction. We demonstrate the proposed approach in the context of discrimination detection, showing that not only it provides 'statistically significant' evidence of discrimination but it also allows for a more efficient operationalization of the recommendations extracted, upon which the decision maker can operate.

    KW - Association Rule Mining

    KW - Decisional Process

    KW - Econometrics

    UR - http://www.scopus.com/inward/record.url?scp=85069971525&partnerID=8YFLogxK

    U2 - 10.1145/3321705.3329856

    DO - 10.1145/3321705.3329856

    M3 - Conference contribution

    SP - 67

    EP - 72

    BT - AsiaCCS 2019 - Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security

    PB - Association for Computing Machinery, Inc

    CY - New York

    ER -

    Genga L, Allodi L, Zannone N. Unveiling systematic biases in decisional processes: an application to discrimination discovery. In AsiaCCS 2019 - Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security. New York: Association for Computing Machinery, Inc. 2019. blz. 67-72. Beschikbaar vanaf, DOI: 10.1145/3321705.3329856