Answer: AUC Curve

The question asks for the best evaluation metric for a binary classification model with imbalanced data. The community discussion strongly supports AUC (Area Under the ROC Curve) as the optimal choice, with 100% of users selecting option B and multiple comments explaining why. AUC is preferred because it measures the model's ability to distinguish between classes across all classification thresholds and is insensitive to class imbalance. In contrast, accuracy (E) is misleading with imbalanced data, as a model predicting only the majority class could achieve high accuracy (e.g., 99% if one class dominates). Other metrics like Mean Absolute Error (C), Root Mean Square Error (F), Relative Absolute Error (A), and Relative Squared Error (D) are more suited to regression tasks, not classification. While some comments note that 'AUC Curve' is technically a misnomer (AUC is the area, not the curve itself), the consensus is that it refers to the standard AUC metric for imbalanced classification.

Author: LeetQuiz Editorial Team