Table 7 Part-B mean and standard deviation of AUC 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 | 0.90846 | 0.93072 | 0.99316 | 0.98621 | 0.97534 |
(0.00086) | (0.00087) | (0.00039) | (0.00039) | (0.00039) | |
1:3 | 0.91054 | 0.93427 | 0.99323 | 0.99219 | 0.98404 |
(0.00078) | (0.00089) | (0.00037) | (0.00028) | (0.00038) | |
1:9 | 0.91087 | 0.93028 | 0.99259 | 0.99394 | 0.98849 |
(0.00102) | (0.00101) | (0.00041) | (0.00025) | (0.00043) | |
1:27 | 0.90664 | 0.92148 | 0.99085 | 0.99443 | 0.99050 |
(0.00241) | (0.00127) | (0.00041) | (0.00032) | (0.00041) | |
1:81 | 0.89803 | 0.91200 | 0.98764 | 0.99458 | 0.99069 |
(0.00530) | (0.00104) | (0.00051) | (0.00028) | (0.00048) | |
Unchanged | 0.88554 | 0.89698 | 0.98118 | 0.99436 | 0.98862 |
(0.00542) | (0.00121) | (0.00080) | (0.00033) | (0.00051) |