The effect of the characteristics of the dataset on the selection stability

Abstract—Feature selection is an effective technique to reduce

the dimensionality of a data set and to select relevant features

for the domain problem. Recently, stability of feature selection

methods has gained increasing attention. In fact, it has become a

crucial factor in determining the goodness of a feature selection

algorithm besides the learning performance. In this work, we

conduct an extensive experimental study using verity of data sets

and different well-known feature selection algorithms in order to

study the behavior of these algorithms in terms of the stability.

Index Terms—Feature selection algorithms, stability, dimensionality

reduction, data distribution, Jaccard Index, sample size.