Metraipolis › archive › dc_a586ee093968
Algorithmic Recourse Under Competition — arXiv:2609.39877
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39877
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:45:51.481Z
- SHA-256 of the archived text
e2b2554aa14cd2c1606f9818abbc5a4e3cb3ba67c434e1e0a96ee65c1e624d82- Stable URL of this page
https://metraipolis.com/documento/dc_a586ee093968
How to cite
Algorithmic Recourse Under Competition — arXiv:2609.39877 — arXiv (en), https://arxiv.org/abs/2609.39877 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a586ee093968 (Metraipolis archive dc_a586ee093968, sha256 e2b2554aa14cd2c1606f9818abbc5a4e3cb3ba67c434e1e0a96ee65c1e624d82)
BibTeX
@misc{dca586ee093968,
title = {Algorithmic Recourse Under Competition — arXiv:2609.39877},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39877},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a586ee093968; sha256 e2b2554aa14cd2c1606f9818abbc5a4e3cb3ba67c434e1e0a96ee65c1e624d82},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39877. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Algorithmic recourse provides individuals who have received undesirable outcomes from machine learning models with suggestions for minimum-cost improvements to achieve the desired outcome. A central assumption when computing recourse is that the decision rule remains fixed throughout the recourse implementation phase. We challenge this assumption in settings where individuals compete for limited resources. In such settings, widespread recourse implementation can change the acceptance threshold even when the scoring model that is used to evaluate individuals remains the same. This change in acceptance threshold can, in turn, invalidate the original recourse recommendations (i.e., following the recourse may not lead to the desired outcome). To address this problem, we introduce a framework called recourse under competition that jointly optimizes for recommendation recipients and the recommended score target they need to satisfy to balance the recourse cost and post-shift validity among initially rejected individuals. We develop an algorithm based on the Implicit Function Theorem and empirically analyze its performance. Experiments on synthetic and real datasets show that personalized score targets can achieve higher validity, albeit at a higher cost. In contrast, common score targets generally offer favorable cost-validity trade-offs for lower to medium validity values. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.39877 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T12:14:14.163Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).