Evaluation of binary classifiers for asymptotically dependent and independent extremes - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Evaluation of binary classifiers for asymptotically dependent and independent extremes

Résumé

Machine learning classification methods usually assume that all possible classes are sufficiently present within the training set. Due to their inherent rarities, extreme events are always under-represented and classifiers tailored for predicting extremes need to be carefully designed to handle this under-representation. In this paper, we address the question of how to assess and compare classifiers with respect to their capacity to capture extreme occurrences. This is also related to the topic of scoring rules used in forecasting literature. In this context, we propose and study a risk function adapted to extremal classifiers. The inferential properties of our empirical risk estimator are derived under the framework of multivariate regular variation and hidden regular variation. A simulation study compares different classifiers and indicates their performance with respect to our risk function. To conclude, we apply our framework to the analysis of extreme river discharges in the Danube river basin. The application compares different predictive algorithms and test their capacity at forecasting river discharges from other river stations. As a byproduct, we study the special class of linear classifiers, show that the optimisation of our risk function leads to a consistent solution and we identify the explanatory variables that contribute the most to extremal behavior.
Fichier principal
Vignette du fichier
2112.13738.pdf (1.04 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04075543 , version 1 (20-04-2023)

Identifiants

Citer

Juliette Legrand, Philippe Naveau, Marco Oesting. Evaluation of binary classifiers for asymptotically dependent and independent extremes. 2023. ⟨hal-04075543⟩
20 Consultations
28 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More