AWS Certified Machine Learning – Specialty — Question 286

A chemical company has developed several machine learning (ML) solutions to identify chemical process abnormalities. The time series values of independent variables and the labels are available for the past 2 years and are sufficient to accurately model the problem.

The regular operation label is marked as 0 The abnormal operation label is marked as 1. Process abnormalities have a significant negative effect on the company’s profits. The company must avoid these abnormalities.

Which metrics will indicate an ML solution that will provide the GREATEST probability of detecting an abnormality?

Answer options

• A. Precision = 0.91 - Recall = 0.6
• B. Precision = 0.61 - Recall = 0.98
• C. Precision = 0.7 - Recall = 0.9
• D. Precision = 0.98 - Recall = 0.8

Correct answer: B

Explanation

To minimize the severe financial impact of undetected chemical process abnormalities, the company must prioritize minimizing False Negatives, which means maximizing the Recall metric. Option B has the highest Recall score of 0.98, indicating it has the highest probability of successfully identifying an abnormality when one occurs. While its Precision is lower, resulting in more false alarms, it ensures that almost no critical anomalies are missed.