Overlaying classiers: a practical approach to optimal scoring - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Constructive Approximation Année : 2010

Overlaying classiers: a practical approach to optimal scoring

Résumé

The ROC curve is one of the most widely used visual tool to evaluate performance of scoring functions regarding their capacities to discriminate between two populations. It is the goal of this paper to propose a statistical learning method for constructing a scoring function with nearly optimal ROC curve. In this bipartite setup, the target is known to be the regression function up to an increasing transform and solving the optimization problem boils down to recovering the collection of level sets of the latter, which we interpret here as a continuum of imbricated classification problems. We propose a discretization approach, consisting in building a finite sequence of N classifiers by constrained empirical risk minimization and then constructing a piecewise constant scoring function sN(x) by overlaying the resulting classifiers. Given the functional nature of the ROC criterion, the accuracy of the ranking induced by sN(x) can be conceived in a variety of ways, depending on the distance chosen for measuring closeness to the optimal curve in the ROC space. By relating the ROC curve of the resulting scoring function to piecewise linear approximates of the optimal ROC curve, we establish the consistency of the method as well as rate bounds to control its generalization ability in sup-norm. Eventually, we also highlight the fact that, as a byproduct, the algorithm proposed provides an accurate estimate of the optimal ROC curve.
Fichier principal
Vignette du fichier
Overlaying_sub.pdf (259.83 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00341246 , version 1 (24-11-2008)

Identifiants

Citer

Stéphan Clémençon, Nicolas Vayatis. Overlaying classiers: a practical approach to optimal scoring. Constructive Approximation, 2010, 32 (3), pp.619-648. ⟨10.1007/s00365-010-9084-9⟩. ⟨hal-00341246⟩
250 Consultations
275 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More