Evaluating causes of algorithmic bias in juvenile criminal recidivism
Mostra el registre complet Registre parcial de l'ítem
- dc.contributor.author Miron, Marius
- dc.contributor.author Tolan, Songül
- dc.contributor.author Gómez Gutiérrez, Emilia, 1975-
- dc.contributor.author Castillo, Carlos
- dc.date.accessioned 2020-07-08T08:35:03Z
- dc.date.available 2020-07-08T08:35:03Z
- dc.date.issued 2020
- dc.description.abstract In this paper we investigate risk prediction of criminal re-offense among juvenile defendants using general-purpose machine learning (ML) algorithms. We show that in our dataset, containing hundreds of cases, ML models achieve better predictive power than a structured professional risk assessment tool, the Structured Assessment of Violence Risk in Youth (SAVRY), at the expense of not satisfying relevant group fairness metrics that SAVRY does satisfy. We explore in more detail two possible causes of this algorithmic bias that are related to biases in the data with respect to two protected groups, foreigners and women. In particular, we look at (1) the differences in the prevalence of re-offense between protected groups and (2) the influence of protected group or correlated features in the prediction. Our experiments show that both can lead to disparity between groups on the considered group fairness metrics. We observe that methods to mitigate the influence of either cause do not guarantee fair outcomes. An analysis of feature importance using LIME, a machine learning interpretability method, shows that some mitigation methods can shift the set of features that ML techniques rely on away from demographics and criminal history which are highly correlated with sensitive features.en
- dc.description.sponsorship Funding was provided by Joint Research Centre (Grant No. HUMAINT).
- dc.format.mimetype application/pdf
- dc.identifier.citation Miron M, Tolan S, Gómez E, Castillo C. Evaluating causes of algorithmic bias in juvenile criminal recidivism. Artif Intell Law. 2020 Jun 7. DOI: 10.1007/s10506-020-09268-y
- dc.identifier.doi http://dx.doi.org/10.1007/s10506-020-09268-y
- dc.identifier.issn 0924-8463
- dc.identifier.uri http://hdl.handle.net/10230/45086
- dc.language.iso eng
- dc.publisher Springer
- dc.relation.ispartof Artificial intelligence and law. 2020 Jun 7
- dc.rights This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
- dc.rights.accessRights info:eu-repo/semantics/openAccess
- dc.rights.uri http://creativecommons.org/licenses/by/4.0/
- dc.subject.keyword Criminal recidivismen
- dc.subject.keyword Machine learningen
- dc.subject.keyword Algorithmic fairnessen
- dc.subject.keyword Risk assessmenten
- dc.subject.keyword Criminal justiceen
- dc.subject.keyword Automated decision makingen
- dc.title Evaluating causes of algorithmic bias in juvenile criminal recidivismen
- dc.type info:eu-repo/semantics/article
- dc.type.version info:eu-repo/semantics/publishedVersion