Predictive Performance of Weighted Relative Accuracy

Todorovski Ljupco, Zighed Djamel A., Peter Flach, Komorowski Jan, Lavrac Nada, Zytkow Jan

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

Abstract

Weighted relative accuracy was proposed in iteilp99-lavrac-flach-zupan as an alternative to classification accuracy typically used in inductive rule learners. Weighted relative accuracy takes into account the improvement of the accuracy relative to the default rule (i.e., the rule stating that the same class should be assigned to all examples), and also explicitly incorporates the generality of a rule (i.e., the number of examples covered). In order to measure the predictive performance of weighted relative accuracy, we implemented it in the rule induction algorithm CN2. Our main results are that weighted relative accuracy dramatically reduces the size of the rule sets induced with CN2 (on average by a factor 9 on the 23 datasets we used), at the expense of only a small average drop in classification accuracy.
Translated title of the contributionPredictive Performance of Weighted Relative Accuracy
Original languageEnglish
Title of host publication4th European Conference on Principles of Data Mining and Knowledge Discovery (PKDD2000)
Pages255-264
Publication statusPublished - 2000

Bibliographical note

ISBN: 354041066X
Publisher: Springer-Verlag
Name and Venue of Conference: 4th European Conference on Principles of Data Mining and Knowledge Discovery (PKDD2000)
Other identifier: 1000516

Cite this