New Year Sale 2026! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions
Mail Us support@pass4success.com
Location US
Mob_nav_barsMENU

Microsoft AI-900 Exam - Topic 7 Question 36 Discussion

Actual exam question for Microsoft's AI-900 exam
Question #: 36
Topic #: 7
[All AI-900 Questions]

Which metric can you use to evaluate a classification model?

Show Suggested Answer Hide Answer
Suggested Answer: A

What does a good model look like?

An ROC curve that approaches the top left corner with 100% true positive rate and 0% false positive rate will be the best model. A random model would display as a flat line from the bottom left to the top right corner. Worse than random would dip below the y=x line.


https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#classification

by Arthur at Oct 14, 2022, 04:42 AM

Limited Time Offer

25%

Off

Get Premium AI-900 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

0/2000 characters
Submit Cancel
Chi
4 months ago
RMSE is for regression too, right? Not sure it fits here.
upvoted 0 times
...
Edna
4 months ago
Wait, can you really use R2 for classification? Seems off.
upvoted 0 times
...
Danilo
4 months ago
Definitely agree with the true positive rate!
upvoted 0 times
...
Stevie
4 months ago
I think MAE is more for regression, not classification.
upvoted 0 times
...
Jettie
5 months ago
True positive rate is a solid choice!
upvoted 0 times
...
Gwenn
5 months ago
RMSE seems familiar, but I can't remember if it's applicable here. I think it’s mostly for regression too.
upvoted 0 times
...
Andra
5 months ago
I feel like R2 is also used for regression, but I can't recall if it has any application in classification.
upvoted 0 times
...
Virgie
5 months ago
I remember practicing with similar questions, and I think MAE is more for regression models, right?
upvoted 0 times
...
Dorcas
5 months ago
I think the true positive rate is definitely a metric for classification models, but I'm not sure if it's the only one we should consider.
upvoted 0 times
...
Cordelia
5 months ago
I'm a little confused by the wording of this question. Can campaign tracking data really come from both Marketing Cloud and Pardot? I'll need to think about the relationship between those two platforms to answer this correctly.
upvoted 0 times
...
Tasia
5 months ago
I think I read somewhere that when test strategies aren't followed, the plans could be considered inconsistent with them. So, I'm leaning toward D, but I'm not completely confident.
upvoted 0 times
...
Tien
5 months ago
I remember discussing the importance of PRACK for reliable provisional responses in SIP scenarios, so I think option C might be the right choice here.
upvoted 0 times
...
Stefan
5 months ago
This seems like a straightforward question about the capabilities of a deactivated Office 365 device. I'll need to think through the different options carefully.
upvoted 0 times
...
Devorah
5 months ago
Hmm, this one seems a bit tricky. I'll need to carefully analyze the details about the redirects and the lack of authentication prompt.
upvoted 0 times
...
Brunilda
5 months ago
Okay, I think I've got this. The asset's carrying value is $230,000, the fair value is $210,000, and the disposal costs are $15,000. So the value to use in the statement of financial position should be the fair value less the disposal costs, which is $195,000.
upvoted 0 times
...

Save Cancel