A data scientist trains a multiclass classification model to identify different species of flowers (Iris setosa, Iris virginica, Iris versicolor). The overall accuracy is 94%, but the accuracy for the Iris virginica class is only 60%. Which additional metric should the data scientist examine to better understand the model's performance on the minority class?

Precision

Precision indicates the fraction of correct predictions among all predictions for that class, but it does not consider false negatives. While useful, F1-score combines precision and recall for a more complete picture.

Recall

Recall indicates the fraction of actual instances of that class that were correctly predicted, but it ignores false positives. F1-score is preferred for a balanced view.

Mean Absolute Error (MAE)

MAE is a metric used for regression models, not classification. It measures the average magnitude of errors in continuous predictions, and is not applicable to flower species classification.

What does this AI-900 question test?

Read the scenario before looking for a memorised answer.

What is the correct answer to this question?

The correct answer is: F1-score — F1-score is the harmonic mean of precision and recall, providing a balanced measure for individual classes, especially when classes are imbalanced. Accuracy alone can be misleading. Precision measures how many of the predicted positive instances are correct. Recall measures how many of the actual positive instances were captured. Mean Absolute Error (MAE) is for regression, not classification. The most informative metric for a specific class in a multiclass problem is F1-score.

What should I do if I get this AI-900 question wrong?

Then try more questions from the same exam bank and focus on understanding why the wrong options are tempting.