AWS Certified Machine Learning – Specialty — Question 267

A data scientist for a medical diagnostic testing company has developed a machine learning (ML) model to identify patients who have a specific disease. The dataset that the scientist used to train the model is imbalanced. The dataset contains a large number of healthy patients and only a small number of patients who have the disease. The model should consider that patients who are incorrectly identified as positive for the disease will increase costs for the company.

Which metric will MOST accurately evaluate the performance of this model?

Answer options

• A. Recall
• B. F1 score
• C. Accuracy
• D. Precision

Correct answer: D

Explanation

Precision is the most appropriate metric because it measures the proportion of identified positives that are actually positive, thereby directly penalizing false positives which increase company costs. Accuracy is highly misleading for imbalanced datasets, while Recall focuses on minimizing false negatives rather than false positives. The F1 score provides a balance between precision and recall, but the specific business constraint of minimizing the financial impact of false positives makes Precision the primary metric to optimize.