Training classifiers for unbalanced distribution and cost-sensitive domains with ROC analysis

Authors:
Xiaolong Zhang;Chuan Jiang;Ming-jian Luo
Affiliations:
School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China;School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China;School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China
Venue:
PKAW'06 Proceedings of the 9th Pacific Rim Knowledge Acquisition international conference on Advances in Knowledge Acquisition and Management
Year:
2006

Citing 9
Cited 0

C4.5: programs for machine learning

C4.5: programs for machine learning
A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems

Machine Learning
Adaptive Fraud Detection

Data Mining and Knowledge Discovery
Learning Decision Trees Using the Area Under the ROC Curve

ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Comparing Naive Bayes, Decision Trees, and SVM with AUC and Accuracy

ICDM '03 Proceedings of the Third IEEE International Conference on Data Mining
Solving multiclass learning problems via error-correcting output codes

Journal of Artificial Intelligence Research
AUC: a statistically consistent and more discriminating measure than accuracy

IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
The use of the area under the ROC curve in the evaluation of machine learning algorithms

Pattern Recognition
AUC: a better measure than accuracy in comparing learning algorithms

AI'03 Proceedings of the 16th Canadian society for computational studies of intelligence conference on Advances in artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

ROC (Receiver Operating Characteristic) has been used as a tool for the analysis and evaluation of two-class classifiers, even the training data embraces unbalanced class distribution and cost-sensitiveness. However, ROC has not been effectively extended to evaluate multi-class classifiers. In this paper, we proposed an effective way to deal with multi-class learning with ROC analysis. An EMAUC algorithm is implemented to transform a multi-class training set into several two-class training sets. Classification is carried out with these two-class training sets. Empirical results demonstrate that the classifiers trained with the proposed algorithm have competitive performance for unbalanced distribution and cost-sensitive domains.