|
Uncertainty-aware predictive modeling for fair data-driven decisions
Kaiser, Patrick
;
Kern, Christoph
;
Rügamer, David
|
Dokumenttyp:
|
Präsentation auf Konferenz
|
|
Erscheinungsjahr:
|
2022
|
|
Veranstaltungstitel:
|
Trustworthy and Socially Responsible Machine Learning (TSRML), Workshop at NeurIPS 2022
|
|
Veranstaltungsort:
|
Online
|
|
Veranstaltungsdatum:
|
09.12.2022
|
|
Verwandte URLs:
|
|
|
Sprache der Veröffentlichung:
|
Englisch
|
|
Einrichtung:
|
Fakultät für Sozialwissenschaften > Social Data Science and Methodology (Keusch 2022-)
|
|
Fachgebiet:
|
310 Statistik
|
|
Freie Schlagwörter (Englisch):
|
fairness in machine learning , uncertainty , distributional regression, safety , profiling , neural networks
|
|
Abstract:
|
Both industry and academia have made considerable progress in developing trustworthy and responsible machine learning (ML) systems. While critical concepts like fairness and explainability are often addressed, the safety of systems is typically not sufficiently taken into account. By viewing data-driven decision systems as socio-technical systems, we draw on the uncertainty in ML literature to show how fairML systems can also be safeML systems. We posit that a fair model needs to be an uncertainty-aware model, e.g. by drawing on distributional regression. For fair decisions, we argue that a safe fail option should be used for individuals with uncertain categorization. We introduce semi-structured deep distributional regression as a modeling framework which addresses multiple concerns brought against standard ML models and show its use in a real-world example of algorithmic profiling of job seekers.
|
 | Dieser Eintrag ist Teil der Universitätsbibliographie. |
 Suche Autoren in
BASE:
Kaiser, Patrick
;
Kern, Christoph
;
Rügamer, David
Google Scholar:
Kaiser, Patrick
;
Kern, Christoph
;
Rügamer, David
ORCID:
Kaiser, Patrick, Kern, Christoph  ORCID: https://orcid.org/0000-0001-7363-4299 and Rügamer, David
Sie haben einen Fehler gefunden? Teilen Sie uns Ihren Korrekturwunsch bitte hier mit: E-Mail
Actions (login required)
 |
Eintrag anzeigen |
|
|
