Table 6. The performance of the Different Machine Learning Models evaluated using the Hold Out method (70/30) using SMOTE.
The RTF model achieve the highest AUC (0.88), Sensitivity (74.30%), Precision (73.50%) and F-Score (73.90%).
| ANN | LB | LWB | RTF | BN | SVM | |
|---|---|---|---|---|---|---|
| Sensitivity | 39.50% | 31.40% | 40.80% | 74.30% | 48.80% | 26.30% |
| Specificity | 86.50% | 88.60% | 81.80% | 85.60% | 79.30% | 88.60% |
| Precision | 61.20% | 59.80% | 54.60% | 73.50% | 55.90% | 55.50% |
| F-score | 48% | 41.20% | 46.64% | 73.90% | 52.10% | 35.70% |
| AUC | 0.72 | 0.70 | 0.70 | 0.88 | 0.71 | 0.58 |
| RMSE | 0.54 | 0.451 | 0.46 | 0.36 | 0.47 | 0.58 |