Improving accuracy and cost of two-class and multi-class probabilistic classifiers using ROC curves

N Lachiche, PA Flach

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

77 Citations (Scopus)

Abstract

The probability estimates of a naive Bayes classifier are inaccurate if some of its underlying independence assumptions are violated. The decision criterion for using these estimates for classification therefore has to be learned from the data. This paper proposes the use of ROC curves for this purpose. For two classes, the algorithm is a simple adaptation of the algorithm for tracing a ROC curve by sorting the instances according to their predicted probability of being positive. As there is no obvious way to upgrade this algorithm to the multi-class case, we propose a hill-climbing approach which adjusts the weights for each class in a pre-defined order. Experiments on a wide range of datasets show the proposed method leads to significant improvements over the naive Bayes classifier's accuracy. Finally, we discuss an method to find the global optimum, and show how its computational complexity would make it untractable.
Translated title of the contributionImproving accuracy and cost of two-class and multi-class probabilistic classifiers using ROC curves
Original languageEnglish
Title of host publicationUnknown
PublisherAAAI Press
Pages416 - 423
Number of pages7
ISBN (Print)1577351894
Publication statusPublished - Jan 2003

Bibliographical note

Conference Proceedings/Title of Journal: Proc. 20th International Conference on Machine Learning (ICML'03)

Fingerprint Dive into the research topics of 'Improving accuracy and cost of two-class and multi-class probabilistic classifiers using ROC curves'. Together they form a unique fingerprint.

Cite this