Table 3 The evaluation metrics for each model using feature subsets
Model | Balanced accuracy | Recall | Precision | F1 score |
|---|---|---|---|---|
Decision Tree | 79.66%(78.13–89.56%) | 85.59%(80.49–97.73%) | 49.80%(43.55–66.68%) | 62.91%(58.00-77.19%) |
SVM | 82.83%(75.11–88.61%) | 82.64%(65.21–90.63%) | 59.71%(48.94–76.09%) | 69.24%(58.53–79.67%) |
Random Forest | 81.09%(81.36–91.42%) | 85.12%(84.44–100.00%) | 53.03%(46.55–71.15%) | 65.31%(62.50-81.08%) |
XGBoost | 82.54%(78.14–91.04%) | 82.21%(67.57–91.90%) | 59.61%(54.90–81.40%) | 68.93%(53.11–92.55%) |
AdaBoost | 77.18%(70.12–85.44%) | 0.5913(81.36–91.42%) | 0.7884(81.36–91.42%) | 0.6758(81.36–91.42%) |