ASSESMENT THE QUALITY OF CLASSIFICATION ALGORITHMS

被引：0
作者：
Skalska, Hana [1 ]
机构：
[1] Univ Hradec Kralove, Fac Informat & Management, Hradec Kralove 50003, Czech Republic
来源：
APLIMAT 2005 - 4TH INTERNATIONAL CONFERENCE, PT II | 2005年
关键词：
Classification; Predictive Accuracy Measures; ROC; EC graph; ROC CURVE; AREA;
D O I：
暂无
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
This article summarizes the latest findings dealing with comparison of predictive accuracy (performance) of classification algorithms. Different measures of performance of classifiers arc described here as well as the possibilities of ROC analysis and their dual representation with expected costs graph.
引用
收藏
页码：529 / 535
页数：7
相关论文
共 12 条
[1]  
Anderson T. W., 1962, An Introduction to Multivariate Statistical Analysis
[2]  
Drummond C., 2000, Proceedings. KDD-2000. Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, P198, DOI 10.1145/347090.347126
[3]  
Fawcett T., 2004, ROC graphs: Notes and practical considerations for researchers
[4]  
Han J., 2012, Data Mining, P393, DOI [DOI 10.1016/C2009-0-61819-5, 10.1016/B978-0-12-381479-1.00009-5, DOI 10.1016/B978-0-12-381479-1.00009-5]
[5]   A simple generalisation of the area under the ROC curve for multiple class classification problems [J].
Hand, DJ ;
Till, RJ .
MACHINE LEARNING, 2001, 45 (02) :171-186
[6]   THE MEANING AND USE OF THE AREA UNDER A RECEIVER OPERATING CHARACTERISTIC (ROC) CURVE [J].
HANLEY, JA ;
MCNEIL, BJ .
RADIOLOGY, 1982, 143 (01) :29-36
[7]   On evaluating performance of classifiers for rare classes [J].
Joshi, MV .
2002 IEEE INTERNATIONAL CONFERENCE ON DATA MINING, PROCEEDINGS, 2002, :641-644
[8]  
KLOSGEN W, 2002, HDB DATA MINING KNOW, P254
[9]  
Martin A., 1997, P EUROSPEECH CURVE A, P1895
[10]  
SKALSKA H, 2003, ROC CURVE AUC ESTIMA
12