Table 8 Part-B mean and standard deviation of AUPRC with varying levels of RUS (10 iterations of fivefold cross-validation)
From: Evaluating classifier performance with highly imbalanced Big Data
Class ratio | LGB | CB-16 | ET | XGB-24 | RF-GPU-32 |
|---|---|---|---|---|---|
1:1 | 0.04621 | 0.05853 | 0.93517 | 0.15584 | 0.26342 |
(0.00253) | (0.00238) | (0.00209) | (0.00419) | (0.01037) | |
1:3 | 0.06426 | 0.08606 | 0.94335 | 0.38531 | 0.42815 |
(0.00217) | (0.00236) | (0.00160) | (0.00786) | (0.00815) | |
1:9 | 0.07818 | 0.11695 | 0.94563 | 0.67304 | 0.56271 |
(0.00513) | (0.00224) | (0.00129) | (0.00795) | (0.00532) | |
1:27 | 0.06664 | 0.14166 | 0.94682 | 0.85988 | 0.70862 |
(0.00761) | (0.00309) | (0.00155) | (0.00376) | (0.00746) | |
1:81 | 0.06128 | 0.15084 | 0.94758 | 0.92030 | 0.80848 |
(0.01261) | (0.00299) | (0.00150) | (0.00167) | (0.00270) | |
Unchanged | 0.06768 | 0.13607 | 0.94990 | 0.93947 | 0.90510 |
(0.01071) | (0.00254) | (0.00162) | (0.00156) | (0.00182) |