Skip to main content

Table 1 Combinations of γ, p, p(rel) and β used for the simulation design

From: Cost-Constrained feature selection in binary classification: adaptations for greedy forward selection and genetic algorithms

Setting A\(\frac {1}{2}\)30180.3
Setting B\(\frac {2}{3}\)3031
Setting C\(\frac {1}{3}\)300300.5
Setting D\(\frac {2}{3}\)30030.5
Setting E21500150.5
Setting F\(\frac {1}{2}\)1500200.5
Setting G\(\frac {1}{3}\)300300.3
Setting H\(\frac {1}{3}\)300300.5
Setting I\(\frac {1}{3}\)30030\(\frac {1}{30}, \frac {2}{30}, \dots, 1\)
Setting J\(\frac {1}{3}\)30030\(\frac {1}{30}, \frac {2}{30}, \dots, 1\)
Setting K\(\frac {1}{3}\)300300.5
  1. For every setting B=100 training data sets are generated. Settings G to K are specialized settings, which focus on changes in the data generation process. For details see “Settings with altered simulation design” section