Skip to main content

ROCCER: an Algorithm for Rule Learning Based on ROC Analysis

Ronaldo C. Prati, Peter A. Flach, ROCCER: an Algorithm for Rule Learning Based on ROC Analysis. Proceedings of the 19th International Joint Conference on Artificial Intelligence (IJCAI'05). ISSN 0938075934, pp. 823–828. August 2005. PDF, 173 Kbytes. External information

Abstract

We introduce a rule selection algorithm called ROCCER, which operates by selecting classification rules from a larger set of rules y for instance found by Apriori y using ROC analysis. Experimental comparison with rule induction algorithms shows that ROCCER tends to produce considerably smaller rule sets with compatible Area Under the ROC Curve (AUC) values. The individual rules that compose the rule set also have higher support and stronger association indexes.

Bibtex entry.

Contact details

Publication Admin