Title :
Instability of classifiers on categorical data
Author :
Siebes, Arno ; Subianto, Muhammad ; Feelders, Ad
Author_Institution :
Dept. of Comput. Sci., Universiteit Utrecht, Netherlands
Abstract :
In this paper we study the local behaviour of arbitrary classifiers using the instability of that classifier in a data point. Moreover, we introduce two algorithms. The first to find highly unstable points, the second to find islands of stability.
Keywords :
data mining; pattern classification; categorical data; classifier instability; data mining; Books; Classification tree analysis; Computer science; Data mining; Information geometry; Performance evaluation; Stability; Support vector machine classification; Support vector machines; Testing;
Conference_Titel :
Data Mining, Fifth IEEE International Conference on
Print_ISBN :
0-7695-2278-5
DOI :
10.1109/ICDM.2005.81
