Skip to main content

Repairing Concavities in ROC Curves

Flach, Peter A. and Wu, Shaomin (2005) Repairing Concavities in ROC Curves. In: Proceedings of the 19th International Joint Conference on Artificial Intelligence. Morgan Kaufmann Publishers Inc., San Francisco, California, USA, pp. 702-707. ISBN 0-938075-93-4. (Unpublished) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:32217)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)
Official URL
http://www.ijcai.org/papers/0652.pdf

Abstract

In this paper we investigate methods to detect and repair concavities in ROC curves by manipulating model predictions. The basic idea is that, if a point or a set of points lies below the line spanned by two other points in ROC space, we can use this information to repair the concavity. This effectively builds a hybrid model combining the two better models with an inversion of the poorer models; in the case of ranking classifiers, it means that certain intervals of the scores are identified as unreliable and candidates for inversion. We report very encouraging results on 23 UCI data sets, particularly for naive Bayes where the use of two validation folds yielded significant improvements on more than half of them, with only one loss.

Item Type: Book section
Subjects: H Social Sciences > HA Statistics > HA33 Management Science
Divisions: Divisions > Kent Business School - Division > Kent Business School (do not use)
Depositing User: Shaomin Wu
Date Deposited: 28 Nov 2012 11:59 UTC
Last Modified: 16 Feb 2021 12:43 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/32217 (The current URI for this page, for reference purposes)
Wu, Shaomin: https://orcid.org/0000-0001-9786-3213
  • Depositors only (login required):