Exam DP-100 topic 3 question 38 discussion

Actual exam question from Microsoft's DP-100

Question #: 38
Topic #: 3

You are evaluating a completed binary classification machine learning model.
You need to use the precision as the evaluation metric.
Which visualization should you use?

A. violin plot
B. Gradient descent
C. Scatter plot
D. Receiver Operating Characteristic (ROC) curve

Show Suggested Answer

Suggested Answer: D 🗳️

by pg13 at June 17, 2021, 2:19 p.m.

Comments

Submit Cancel

spaceykacey

Highly Voted 3 years ago

I will go with D. However, it should be PR curve or F1 score or confusion matrix. You cannot visualise precision with ROC curve.

upvoted 9 times

David_Tadeu

2 years, 8 months ago

Yes, the ROC curve gives the sensitivity (recall) = TP/(TP+FN), not the precision = TP/(TP+FP).

upvoted 1 times

...

synapse

Highly Voted 2 years, 8 months ago

Selected Answer: D

D Copying a good answer: None of I will go with D. However, it should be PR curve or F1 score or confusion matrix. You cannot visualise precision with ROC curve.the answers are correct. I think D is the best answer.

upvoted 5 times

...