Definition:
Evaluation metrics are used to measure the performance of AI and machine learning models. They help determine how accurately a model predicts or classifies data.
1. Accuracy
Percentage of correct predictions
Suitable for balanced datasets
2. Precision
Proportion of true positive predictions among all positive predictions
Important when false positives are costly
3. Recall (Sensitivity)
Proportion of true positives detected among all actual positives
Important when false negatives are costly
4. F1-Score
Harmonic mean of Precision and Recall
Balances both metrics
5. Mean Squared Error (MSE)
Measures error in regression problems
Average squared difference between predicted and actual values
6. ROC-AUC
Measures classification model performance at different thresholds
Higher AUC = better model
Choosing the right metric depends on the problem type (classification vs regression) and business goals.
Take quizzes related to this topic and see where you stand!
Start Quiz Now