Log Anomaly Detection on Jhuisi (test)
100PrecisionCoLog
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| CoLogSupervision Type=Supervised2025.12 | 100 | 100 | 100 | 100 | |
| pylogsentimentSupervision Type=Supervised2025.12 | 98.867 | 98.761 | 98.813 | 98.85 | |
| Convolutional Neural NetworkSupervision Type=Supervised2025.12 | 97.139 | 94.885 | 95.982 | 99.341 | |
| LSTMSupervision Type=Unsupervised2025.12 | 96.879 | 92.385 | 94.508 | 99.121 | |
| TransformerSupervision Type=Unsupervised2025.12 | 96.879 | 92.385 | 94.508 | 99.121 | |
| Attentional BiLSTMSupervision Type=Supervised2025.12 | 95.123 | 97.27 | 96.169 | 99.341 | |
| Decision TreeSupervision Type=Supervised2025.12 | 91.534 | 89.769 | 90.55 | 93.313 | |
| Logistic RegressionSupervision Type=Supervised2025.12 | 68.373 | 66.127 | 64.886 | 79.182 | |
| Support Vector MachinesSupervision Type=Supervised2025.12 | 63.643 | 66.506 | 64.051 | 80.914 | |
| Isolation ForestSupervision Type=Unsupervised2025.12 | 57.519 | 52.774 | 51.7 | 74.707 | |
| Principal Component AnalysisSupervision Type=Unsupervised2025.12 | 44.828 | 49.299 | 45.014 | 75.448 |