Table 5 Model performance on training set.
From: Machine learning detection of manipulative environmental disclosures in corporate reports
Model | Accuracy | F1-Score | ROC-AUC | PR-AUC | Balanced accuracy | MCC | Variance reduced (%) | Overfitting indicator |
|---|---|---|---|---|---|---|---|---|
Logistic Regression (LR) | 0.9926 | 0.99 | 0.5 | 0.74 | 0.83 | 0.71 | Low | High |
Decision Trees (DT) | 0.9927 | 0.99 | 0.5064 | 0.76 | 0.84 | 0.72 | Moderate | Moderate |
Random Forest (RF) | 0.9967 | 0.99 | 0.7809 | 0.78 | 0.86 | 0.73 | High | Low |
