German Credit
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Global Counterfactual Explanations | German Credit | Effectiveness100 | 36 | |
| Credit Risk Prediction | German Credit (test) | Clean Accuracy69.7 | 31 | |
| Coreset Construction | German Credit | Wasserstein Distance0.23 | 28 | |
| Classification | German Credit (test) | Accuracy77.66 | 28 | |
| Binary decision | German Credit | Accuracy68.9 | 27 | |
| Classification | German Credit UCIrvine | Macro F185.32 | 25 | |
| DP Synthetic Data Generation | German Credit | TSTR78.1 | 24 | |
| Predictive modeling | German credit | Accuracy (Acc)81.25 | 20 | |
| Classification | German Credit UCIrvine (5-fold cross-val) | Macro F10.796 | 17 | |
| Classification | German Credit | F1 Score92.5 | 15 | |
| Fair Classification | German Credit (test) | Equal Opportunity Difference5.15 | 15 | |
| Fairness Mitigation | German Credit | AOD-0.0961 | 12 | |
| Fairness Mitigation Evaluation | German Credit (test) | DPD-0.1068 | 12 | |
| Classification | German Credit | AU-ARC0.8388 | 10 | |
| Tabular Synthetic Data Generation | German Credit | KS Statistic0.022 | 8 | |
| Classification | German Credit | Classification Error33 | 8 | |
| Tabular Data Generation | German Credit | Peak Memory Usage (GB)2.2 | 7 | |
| Distribution Alignment | German Credit | MMD0.0549 | 7 | |
| Classification | German Credit | AUROC76.4 | 7 | |
| Counterfactual Explanation Generation | German Credit Protocol A B=4 | Sparsity88.23 | 6 | |
| Distributional Counterfactual Explanations | German Credit tabular (Diff.) | OT Cost (x)0.0182 | 5 | |
| Selective Classification | German Credit | AU-ARC83.8 | 5 | |
| Tabular Classification | GE (German Credit) (test) | MLE Loss0.406 | 5 | |
| Distributional Counterfactual Explanations | German Credit Non-diff. | OT Cost (x)0.0029 | 4 | |
| Node Classification | German Credit (test) | AUROC59.88 | 4 |
Showing 25 of 31 rows