Table 5.
Mean balanced accuracy and F1-score of different types of trained models. We trained several types of models on the same set of the 6 most important features and evaluated their average metrics over 20 runs. Between each run, the train-test split was resampled, maintaining the 80:20 ratio.
| Model trained (20 runs) | Accuracy (SD) | F1-score (SD) |
| Random forest classifier | 0.7429 (0.140) | 0.7311 (0.1707) |
| Decision tree regression | 0.5999 (0.1245) | 0.5862 (0.1455) |
| Support vector classifier | 0.6071 (0.1268) | 0.5816 (0.1622) |
| Multilayer perceptron classifier | 0.5214 (0.1707) | 0.3740 (0.1939) |