Show simple item record

dc.contributor.author
Li, Nianyun
dc.contributor.author
Goel, Naman
dc.contributor.author
Ash, Elliott
dc.date.accessioned
2022-10-10T06:34:30Z
dc.date.available
2022-09-13T06:33:44Z
dc.date.available
2022-10-10T06:34:30Z
dc.date.issued
2022-07
dc.identifier.isbn
978-1-4503-9247-1
en_US
dc.identifier.other
10.1145/3514094.3534147
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/570271
dc.identifier.doi
10.3929/ethz-b-000570271
dc.description.abstract
Notwithstanding the widely held view that data generation and data curation processes are prominent sources of bias in machine learning algorithms, there is little empirical research seeking to document and understand the specific data dimensions affecting algorithmic unfairness. Contra the previous work, which has focused on modeling using simple, small-scale benchmark datasets, we hold the model constant and methodically intervene on relevant dimensions of a much larger, more diverse dataset. For this purpose, we introduce a new dataset on recidivism in 1.5 million criminal cases from courts in the U.S. state of Wisconsin, 2000-2018. From this main dataset, we generate multiple auxiliary datasets to simulate different kinds of biases in the data. Focusing on algorithmic bias toward different race/ethnicity groups, we assess the relevance of training data size, base rate difference between groups, representation of groups in the training data, temporal aspects of data curation, including race/ethnicity or neighborhood characteristics as features, and training separate classifiers by race/ethnicity or crime type. We find that these factors often do influence fairness metrics holding the classifier specification constant, without having a corresponding effect on accuracy metrics. The methodology and the results in the paper provide a useful reference point for a data-centric approach to studying algorithmic fairness in recidivism prediction and beyond.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
Association for Computing Machinery
en_US
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
dc.subject
Algorithmic Fairness
en_US
dc.subject
Datasets
en_US
dc.subject
Recidivism Prediction
en_US
dc.subject
Machine Learning
en_US
dc.title
Data-Centric Factors in Algorithmic Fairness
en_US
dc.type
Conference Paper
dc.rights.license
Creative Commons Attribution 4.0 International
dc.date.published
2022-07-27
ethz.book.title
AIES '22: Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society
en_US
ethz.pages.start
396
en_US
ethz.pages.end
410
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.event
AAAI/ACM Conference on AI, Ethics, and Society (AIES 2022)
en_US
ethz.event.location
Oxford, United Kingdom
ethz.event.date
May 19-21, 2021
ethz.identifier.scopus
ethz.publication.place
New York, NY
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02045 - Dep. Geistes-, Sozial- u. Staatswiss. / Dep. of Humanities, Social and Pol.Sc.::09627 - Ash, Elliott / Ash, Elliott
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02045 - Dep. Geistes-, Sozial- u. Staatswiss. / Dep. of Humanities, Social and Pol.Sc.::09627 - Ash, Elliott / Ash, Elliott
ethz.date.deposited
2022-09-13T06:33:50Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2022-10-10T06:34:31Z
ethz.rosetta.lastUpdated
2024-02-02T18:24:49Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Data-Centric%20Factors%20in%20Algorithmic%20Fairness&rft.date=2022-07&rft.spage=396&rft.epage=410&rft.au=Li,%20Nianyun&Goel,%20Naman&Ash,%20Elliott&rft.isbn=978-1-4503-9247-1&rft.genre=proceeding&rft_id=info:doi/10.1145/3514094.3534147&rft.btitle=AIES%20'22:%20Proceedings%20of%20the%202022%20AAAI/ACM%20Conference%20on%20AI,%20Ethics,%20and%20Society
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record