Fig. 3From: Cost-Constrained feature selection in binary classification: adaptations for greedy forward selection and genetic algorithmsPerformance results for simulation Settings A to K. Boxplots for every feature selection method illustrate the distribution of the AUC values obtained in the 100 data sets (transparent dots). The black diamonds depict the mean AUC values. A horizontal bar highlights the area between the 0.05 and 0.95 quantile of AUC values when always selecting the cheapest subset (green) or the best real cFS subset (golden) of relevant features that fit in the budget. Both correspond to a univariately optimal solutionBack to article page