15 Evaluation Metrics for Different Types of Learning — Use Case and Special Consideration

Photo by Milad Fakurian on Unsplash

Classification and regression models have distinct evaluation metrics, reflecting the differences in the nature of their predictions. Let’s compare the evaluation metrics commonly used for both types of models:

I. Classification Evaluation Metrics:

1. Accuracy:

• Definition: The ratio of correctly predicted instances to the total instances.
• Use Case: Suitable for balanced datasets.
• Considerations: May be misleading in the presence of imbalanced classes.

2. Precision:

• Definition: The ratio of true positive predictions to the sum of true positives and false positives.
• Use Case: Emphasizes the relevance of positive predictions.
• Considerations: May not be suitable if false negatives are critical.

3. Recall (Sensitivity or True Positive Rate):

• Definition: The ratio of true positive predictions to the sum of true positives and false negatives.
• Use Case: Emphasizes the ability to capture all positive instances.