Table 6.
Execution time comparison of each model along with best-achieved accuracy.
| Prediction Model (PM) | Classifiers with Proposed Approaches | Accuracy | Time (s) |
|---|---|---|---|
| PM1: SVM | Linear SVM | 98.68 | 0.03 |
| Polynomial SVM | 99.03 | 0.03 | |
| PM2: LR | Basic LR | 96.66 | 0.266 |
| LR Predication with 100% Recall | 93.9 | 0.87 | |
| LR with RFE | 98.06 | 0.483 | |
| PM3: KNN | Basic KNN | 95.43 | 0.031 |
| KNN Performance with hyperparameter | 97.35 | 4.023 | |
| PM4: Ensemble Classifier | Ensemble LR | 97.01 | 0.634 |
| CV Prediction with 100% Recall | 92.1 | 1.845 | |
| Voting Classifier (CV) | 97.61 | 0.611 |