Exam AWS Certified Machine Learning - Specialty topic 1 question 344 discussion

Exam question from Amazon's AWS Certified Machine Learning - Specialty

Question #: 344
Topic #: 1

[All AWS Certified Machine Learning - Specialty Questions]

A machine learning (ML) engineer is creating a binary classification model. The ML engineer will use the model in a highly sensitive environment.

There is no cost associated with missing a positive label. However, the cost of making a false positive inference is extremely high.

What is the most important metric to optimize the model for in this scenario?

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

Show Suggested Answer

Suggested Answer: B 🗳️

by MultiCloudIronMan at Sept. 22, 2024, 5:39 p.m.

Disclaimers:

- ExamTopics website is not related to, affiliated with, endorsed or authorized by Amazon.
- Trademarks, certification & product names are used for reference only and belong to Amazon.

Comments

Submit Cancel

spinatram

7 months, 4 weeks ago

when FP cost is higher and important = precision when FN cost is higher and important = recall

upvoted 1 times

...

7f1fe73

8 months ago

Selected Answer: B

In this scenario, the most important metric to optimize for is precision. Precision measures the proportion of true positive predictions among all positive predictions made by the model. Since the cost of making a false positive inference is extremely high, optimizing for precision will help minimize the number of false positives

upvoted 1 times

...

MultiCloudIronMan

9 months, 1 week ago

Selected Answer: B

from Copilot - In this scenario, the most important metric to optimize for is precision. Precision measures the proportion of true positive predictions among all positive predictions made by the model. Since the cost of making a false positive inference is extremely high, optimizing for precision will help minimize the number of false positives

upvoted 1 times

...