Export Ready — 

Setting the Right Expectations

Bibliographic Details
Main Author: Fonseca, João
Publication Date: 2023
Other Authors: Bell, Andrew, Abrate, Carlo, Bonchi, Francesco, Stoyanovich, Julia
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/10362/160269
Summary: Fonseca, J., Bell, A., Abrate, C., Bonchi, F., & Stoyanovich, J. (2023). Setting the Right Expectations: Algorithmic Recourse Over Time. In Proceedings of 2023 ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO ’23) [29] ACM - Association for Computing Machinery. https://doi.org/10.48550/arXiv.2309.06969, https://doi.org/10.1145/3617694.3623251---This research was supported in part by NSF Awards No. 1916505 and 192265, by the NSF Graduate Research Fellowship under Award No. DGE-2234660, by research grants from the Portuguese Foundation for Science and Technology (“Fundação para a Ciência e a Tecnologia”) references SFRH/BD/151473/2021 and UIDB/04152/2020, and by the New York University Center for Responsible AI.
id RCAP_fc824e0b0f91dc05f40845c331e41b55
oai_identifier_str oai:run.unl.pt:10362/160269
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Setting the Right ExpectationsAlgorithmic Recourse Over TimeAlgorithmic recourseCounterfactual ExplanationsExplainable AIDynamic SystemsHuman-Computer InteractionComputer Networks and CommunicationsComputer Vision and Pattern RecognitionSoftwareFonseca, J., Bell, A., Abrate, C., Bonchi, F., & Stoyanovich, J. (2023). Setting the Right Expectations: Algorithmic Recourse Over Time. In Proceedings of 2023 ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO ’23) [29] ACM - Association for Computing Machinery. https://doi.org/10.48550/arXiv.2309.06969, https://doi.org/10.1145/3617694.3623251---This research was supported in part by NSF Awards No. 1916505 and 192265, by the NSF Graduate Research Fellowship under Award No. DGE-2234660, by research grants from the Portuguese Foundation for Science and Technology (“Fundação para a Ciência e a Tecnologia”) references SFRH/BD/151473/2021 and UIDB/04152/2020, and by the New York University Center for Responsible AI.Algorithmic systems are often called upon to assist in high-stakes decision making. In light of this, algorithmic recourse, the principle wherein individuals should be able to take action against an undesirable outcome made by an algorithmic system, is receiving growing attention. The bulk of the literature on algorithmic recourse to-date focuses primarily on how to provide recourse to a single individual, overlooking a critical element: the effects of a continuously changing context. Disregarding these effects on recourse is a significant oversight, since, in almost all cases, recourse consists of an individual making a first, unfavorable attempt, and then being given an opportunity to make one or several attempts at a later date — when the context might have changed. This can create false expectations, as initial recourse recommendations may become less reliable over time due to model drift and competition for access to the favorable outcome between individuals. In this work we propose an agent-based simulation framework for studying the effects of a continuously changing environment on algorithmic recourse. In particular, we identify two main effects that can alter the reliability of recourse for individuals represented by the agents: (1) competition with other agents acting upon recourse, and (2) competition with new agents entering the environment. Our findings highlight that only a small set of specific parameterizations result in algorithmic recourse that is reliable for agents over time. Consequently, we argue that substantial additional work is needed to understand recourse reliability over time, and to develop recourse methods that reward agents’ effort.ACM - Association for Computing MachineryNOVA Information Management School (NOVA IMS)Information Management Research Center (MagIC) - NOVA Information Management SchoolRUNFonseca, JoãoBell, AndrewAbrate, CarloBonchi, FrancescoStoyanovich, Julia2023-11-21T23:09:05Z2023-10-302023-10-30T00:00:00Zconference objectinfo:eu-repo/semantics/publishedVersion11application/pdfhttp://hdl.handle.net/10362/160269eng979-8-4007-0381-2PURE: 76190770https://doi.org/10.48550/arXiv.2309.06969info:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-05-22T18:15:56Zoai:run.unl.pt:10362/160269Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:46:36.293647Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Setting the Right Expectations
Algorithmic Recourse Over Time
title Setting the Right Expectations
spellingShingle Setting the Right Expectations
Fonseca, João
Algorithmic recourse
Counterfactual Explanations
Explainable AI
Dynamic Systems
Human-Computer Interaction
Computer Networks and Communications
Computer Vision and Pattern Recognition
Software
title_short Setting the Right Expectations
title_full Setting the Right Expectations
title_fullStr Setting the Right Expectations
title_full_unstemmed Setting the Right Expectations
title_sort Setting the Right Expectations
author Fonseca, João
author_facet Fonseca, João
Bell, Andrew
Abrate, Carlo
Bonchi, Francesco
Stoyanovich, Julia
author_role author
author2 Bell, Andrew
Abrate, Carlo
Bonchi, Francesco
Stoyanovich, Julia
author2_role author
author
author
author
dc.contributor.none.fl_str_mv NOVA Information Management School (NOVA IMS)
Information Management Research Center (MagIC) - NOVA Information Management School
RUN
dc.contributor.author.fl_str_mv Fonseca, João
Bell, Andrew
Abrate, Carlo
Bonchi, Francesco
Stoyanovich, Julia
dc.subject.por.fl_str_mv Algorithmic recourse
Counterfactual Explanations
Explainable AI
Dynamic Systems
Human-Computer Interaction
Computer Networks and Communications
Computer Vision and Pattern Recognition
Software
topic Algorithmic recourse
Counterfactual Explanations
Explainable AI
Dynamic Systems
Human-Computer Interaction
Computer Networks and Communications
Computer Vision and Pattern Recognition
Software
description Fonseca, J., Bell, A., Abrate, C., Bonchi, F., & Stoyanovich, J. (2023). Setting the Right Expectations: Algorithmic Recourse Over Time. In Proceedings of 2023 ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO ’23) [29] ACM - Association for Computing Machinery. https://doi.org/10.48550/arXiv.2309.06969, https://doi.org/10.1145/3617694.3623251---This research was supported in part by NSF Awards No. 1916505 and 192265, by the NSF Graduate Research Fellowship under Award No. DGE-2234660, by research grants from the Portuguese Foundation for Science and Technology (“Fundação para a Ciência e a Tecnologia”) references SFRH/BD/151473/2021 and UIDB/04152/2020, and by the New York University Center for Responsible AI.
publishDate 2023
dc.date.none.fl_str_mv 2023-11-21T23:09:05Z
2023-10-30
2023-10-30T00:00:00Z
dc.type.driver.fl_str_mv conference object
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/160269
url http://hdl.handle.net/10362/160269
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 979-8-4007-0381-2
PURE: 76190770
https://doi.org/10.48550/arXiv.2309.06969
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 11
application/pdf
dc.publisher.none.fl_str_mv ACM - Association for Computing Machinery
publisher.none.fl_str_mv ACM - Association for Computing Machinery
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833596954251100160

Similar Items