On the Application and Impact of differential privacy and Fairness in Ambulance Engagement Time Prediction - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

On the Application and Impact of differential privacy and Fairness in Ambulance Engagement Time Prediction

Résumé

This study elaborates on a complete pipeline for the development of a private and fair Machine Learning (ML) model to predict ambulance engagement time. It was shown that sensitive variables reduced their impact on model building with Random Forest as the differential privacy budget (ϵ) decreased with the GRR and Geometric mechanisms. Also, the application of the Reweighing fairness mechanism negatively affected fairness in private models. Finally, it is possible to keep firefighters' and victims' privacy, recovering an ML model with good performance.
Fichier principal
Vignette du fichier
52_on_the_application_and_impact_.pdf (348.39 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04349309 , version 1 (18-12-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04349309 , version 1

Citer

Selene Cerna, Catuscia Palamidessi. On the Application and Impact of differential privacy and Fairness in Ambulance Engagement Time Prediction. ICLR 2023 - The First Tiny Papers Track at ICLR 2023, May 2023, Kigali, Rwanda. ⟨hal-04349309⟩
45 Consultations
16 Téléchargements

Partager

Gmail Facebook X LinkedIn More