Results of the evaluation metrics for each under-sampling method
| Under-sampling method | AUPRC | MAUC | G-mean | MMCC |
|---|---|---|---|---|
| RUS | 0.631 | 0.783 | 0.532 | 0.243 |
| Near Miss | 0.663 | 0.922 | 0.760 | 0.564 |
| OSS | 0.671 | 0.912 | 0.777 | 0.571 |
| NCR | 0.823 | 0.974 | 0.911 | 0.814 |
| Under-sampling method | G-mean | |||
|---|---|---|---|---|
| RUS | 0.631 | 0.783 | 0.532 | 0.243 |
| Near Miss | 0.663 | 0.922 | 0.760 | 0.564 |
| 0.671 | 0.912 | 0.777 | 0.571 | |
| 0.823 | 0.974 | 0.911 | 0.814 |
Note(s): AUPRC, Area Under the Precision-Recall Curve; MAUC, Mean Area Under the Curve; MMCC, Mean Mathews Correlation Coefficient; RUS, Random Under-sampler; OSS, One-sided Selection; NCR, Neighborhood Cleaning Rule. For each of the evaluation metrics, a higher score (closer to 1) represents a better prediction performance
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.