A bias correction function for classification performance assessment in two-class imbalanced problems

作者: Vicente García , Ramón A Mollineda , J Salvador Sánchez , None

DOI: 10.1016/J.KNOSYS.2014.01.021

关键词:

摘要: This paper introduces a framework that allows to mitigate the impact of class imbalance on most scalar performance measures when used evaluate behavior classifiers. Formally, correction function is defined with aim highlighting those classification results present moderately higher prediction rates minority class. Besides, this punishes scenarios are biased towards majority class, but also strongly favor strategy assumes typical task, in which contains relevant samples research purposes. A novel experimental designed show advantages our approach compared standard use well-established measures, demonstrating its consistency and validity.

参考文章(51)
Troy Raeder, George Forman, Nitesh V. Chawla, Learning from Imbalanced Data: Evaluation Matters Springer Berlin Heidelberg. pp. 315- 331 ,(2012) , 10.1007/978-3-642-23166-7_12
John S. Baras, Alvaro A. Cárdenas, B-ROC curves for the assessment of classifiers over imbalanced data sets national conference on artificial intelligence. pp. 1581- 1584 ,(2006)
Nguyen Thai-Nghe, Zeno Gantner, Lars Schmidt-Thieme, An Evaluation Measure for Learning from Imbalanced Data Based on Asymmetric Beta Distribution Classification and Data Mining. pp. 121- 129 ,(2013) , 10.1007/978-3-642-28894-4_15
Stan Matwin, Miroslav Kubat, Addressing the Curse of Imbalanced Training Sets: One-Sided Selection. international conference on machine learning. pp. 179- 186 ,(1997)
Josiah Poon, Cheng G. Weng, A new evaluation measure for imbalanced datasets australasian data mining conference. pp. 27- 32 ,(2008)
Marina Sokolova, Khaled El Emam, Sadrul Chowdhury, Emilio Neri, Sean Rose, Elizabeth Jonker, Evaluation of Rare Event Detection Advances in Artificial Intelligence. pp. 379- 383 ,(2010) , 10.1007/978-3-642-13059-5_51
Janez Demšar, Statistical Comparisons of Classifiers over Multiple Data Sets Journal of Machine Learning Research. ,vol. 7, pp. 1- 30 ,(2006)
Miroslav Kubat, Robert Holte, Stan Matwin, Learning When Negative Examples Abound european conference on machine learning. pp. 146- 153 ,(1997) , 10.1007/3-540-62858-4_79
Johannes Fürnkranz, Peter A. Flach, An analysis of rule evaluation metrics international conference on machine learning. pp. 202- 209 ,(2003)
Kenneth Kennedy, Brian Mac Namee, Sarah Jane Delany, Learning without default: a study of one-class classification and the low-default portfolio problem AICS'09 Proceedings of the 20th Irish conference on Artificial intelligence and cognitive science. pp. 174- 187 ,(2009) , 10.1007/978-3-642-17080-5_20