List common evaluation metrics for classification tasks.

List common evaluation metrics for classification tasks.

• A. Precision, Recall, F1 Score
• B. ROC-AUC only
• C. Accuracy, precision, recall, F1 score, and ROC-AUC
• D. Accuracy only

Answer: (C)

In classification tasks, evaluating performance with multiple metrics gives a fuller picture of how the model behaves. Accuracy measures overall correctness but can be misleading on imbalanced data. Precision tells you how reliable positive predictions are, while recall shows how well you’re capturing actual positives. The F1 score combines precision and recall to balance them. ROC-AUC assesses the model’s ability to rank positive instances above negative ones across all thresholds, providing a threshold-independent view of discrimination. Because each metric captures different aspects, using accuracy, precision, recall, F1 score, and ROC-AUC together gives a complete set of common evaluation measures.

In classification tasks, evaluating performance with multiple metrics gives a fuller picture of how the model behaves. Accuracy measures overall correctness but can be misleading on imbalanced data. Precision tells you how reliable positive predictions are, while recall shows how well you’re capturing actual positives. The F1 score combines precision and recall to balance them. ROC-AUC assesses the model’s ability to rank positive instances above negative ones across all thresholds, providing a threshold-independent view of discrimination. Because each metric captures different aspects, using accuracy, precision, recall, F1 score, and ROC-AUC together gives a complete set of common evaluation measures.