Kondmann, Lukas und Zhu, Xiao Xiang (2021) Under the Radar - Auditing Fairness in ML for Humanitarian Mapping. 2nd Data-driven Humanitarian Mapping Workshop at KDD, 2021-08-15, virtuell.
![]() |
PDF
4MB |
Offizielle URL: https://kdd-humanitarian-mapping.herokuapp.com/
Kurzfassung
Humanitarian mapping from space with machine learning helps policy-makers to timely and accurately identify people in need. However, recent concerns around fairness and transparency of algorithmic decision-making are a significant obstacle for applying these methods in practice. In this paper, we study if humanitarian mapping approaches from space are prone to bias in their predictions. We map village-level poverty and electricity rates in India based on nighttime lights (NTLs) with linear regression and random forest and analyze if the predictions systematically show prejudice against scheduled caste or tribe communities. To achieve this, we design a causal approach to measure counterfactual fairness based on propensity score matching. This allows to compare villages within a community of interest to synthetic counterfactuals. Our findings indicate that poverty is systematically overestimated and electricity systematically underestimated for scheduled tribes in comparison to a synthetic counterfactual group of villages. The effects have the opposite direction for scheduled castes where poverty is underestimated and electrification overestimated. These results are a warning sign for a variety of applications in humanitarian mapping where fairness issues would compromise policy goals.
elib-URL des Eintrags: | https://elib.dlr.de/143412/ | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Konferenzbeitrag (Poster) | ||||||||||||
Titel: | Under the Radar - Auditing Fairness in ML for Humanitarian Mapping | ||||||||||||
Autoren: |
| ||||||||||||
Datum: | August 2021 | ||||||||||||
Referierte Publikation: | Ja | ||||||||||||
Open Access: | Ja | ||||||||||||
Gold Open Access: | Nein | ||||||||||||
In SCOPUS: | Nein | ||||||||||||
In ISI Web of Science: | Nein | ||||||||||||
Seitenbereich: | Seiten 1-7 | ||||||||||||
Status: | veröffentlicht | ||||||||||||
Stichwörter: | Humanitarian Mapping, Nighttime Lights, Fairness | ||||||||||||
Veranstaltungstitel: | 2nd Data-driven Humanitarian Mapping Workshop at KDD | ||||||||||||
Veranstaltungsort: | virtuell | ||||||||||||
Veranstaltungsart: | internationale Konferenz | ||||||||||||
Veranstaltungsdatum: | 15 August 2021 | ||||||||||||
HGF - Forschungsbereich: | Luftfahrt, Raumfahrt und Verkehr | ||||||||||||
HGF - Programm: | Raumfahrt | ||||||||||||
HGF - Programmthema: | Erdbeobachtung | ||||||||||||
DLR - Schwerpunkt: | Raumfahrt | ||||||||||||
DLR - Forschungsgebiet: | R EO - Erdbeobachtung | ||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | R - Künstliche Intelligenz | ||||||||||||
Standort: | Oberpfaffenhofen | ||||||||||||
Institute & Einrichtungen: | Institut für Methodik der Fernerkundung > EO Data Science | ||||||||||||
Hinterlegt von: | Kondmann, Lukas | ||||||||||||
Hinterlegt am: | 12 Aug 2021 17:42 | ||||||||||||
Letzte Änderung: | 24 Apr 2024 20:43 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags