Skip to main content

Table 4 A sample list of meta-features used in current study

From: Using meta-learning for automated algorithms selection and configuration: an experimental framework for industrial big data

Meta-feature

Description

Nbr_Instances

Number of dataset instances

Nbr_Classes

Number of classes

Class_Entropy

Class entropy

Nbr_Features

Number of features

Skew_min/max/mean

Min, max and mean skewness of numerical features

Kurtosis_min/max/mean

Min, max and mean kurtosis of numerical features

Class/Attr kurtosis

The distribution probability of classes/attributes