AWS Certified Machine Learning Engineer – Associate (MLA-C01) — Question 162

An ML engineer is analyzing a classification dataset before training a model in Amazon SageMarker AI. The ML engineer suspects that the dataset has a significant imbalance between class labels that could lead to biased model predictions. To confirm class imbalance, the ML engineer needs to select an appropriate pre-training bias metric.

Which metric will meet this requirement?

Answer options

• A. Mean square error (MSE)
• B. Difference in proportions of labels (DPL)
• C. Silhouette score
• D. Structural similarity index measure (SSIM)

Correct answer: B

Explanation

The Difference in proportions of labels (DPL) is the appropriate metric to assess class imbalance, as it quantifies the disparity between different class labels. Mean square error (MSE) is used for regression tasks, while Silhouette score and Structural similarity index measure (SSIM) are not relevant for evaluating class imbalance in a classification context.