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 DP-100 Exam - Topic 3 Question 35 Discussion

Actual exam question for Microsoft's DP-100 exam
Question #: 35
Topic #: 3
[All DP-100 Questions]

You are creating a classification model for a banking company to identify possible instances of credit card fraud. You plan to create the model in Azure Machine Learning by using automated machine learning.

The training dataset that you are using is highly unbalanced.

You need to evaluate the classification model.

Which primary metric should you use?

Show Suggested Answer Hide Answer
Suggested Answer: C

AUC_weighted is a Classification metric.

Note: AUC is the Area under the Receiver Operating Characteristic Curve. Weighted is the arithmetic mean of the score for each class, weighted by the number of true instances in each class.


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

by Lavera at May 06, 2022, 04:04 AM

Limited Time Offer

25%

Off

Get Premium DP-100 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

0/2000 characters
Submit Cancel
Alana
4 months ago
AUC is definitely the way to go!
upvoted 0 times
...
Carla
4 months ago
Normalized mean absolute error? That's not the right choice.
upvoted 0 times
...
Quiana
4 months ago
Wait, why not use precision or recall instead?
upvoted 0 times
...
Lorita
5 months ago
Totally agree, accuracy isn't reliable here!
upvoted 0 times
...
Zona
5 months ago
AUC.weighted is best for unbalanced datasets.
upvoted 0 times
...
Marnie
5 months ago
I keep getting confused between AUC and accuracy; I just hope I remember the right one during the exam!
upvoted 0 times
...
Fabiola
5 months ago
I practiced a similar question, and I think AUC.weighted is often preferred in these cases, but I could be mixing it up with something else.
upvoted 0 times
...
Monte
5 months ago
I'm not entirely sure, but I feel like accuracy isn't a good metric for this situation since it can be misleading with imbalanced classes.
upvoted 0 times
...
Julene
5 months ago
I remember we discussed the importance of using AUC for unbalanced datasets, so I think C might be the right choice.
upvoted 0 times
...
Carlene
5 months ago
This is a tricky one. The question mentions a withdrawal design, so the best response measure might be the frequency of reinforcer delivery, since that could be the key variable being manipulated. I'm not totally sure, but I'll go with D just to be safe.
upvoted 0 times
...
Carin
5 months ago
This seems like a straightforward question about entity scoping. I'm pretty confident I know the answer.
upvoted 0 times
...
Macy
5 months ago
I think I remember that Layer 2 VPNs typically use AToM, but I'm not entirely sure how that differentiates from Layer 3.
upvoted 0 times
...
Lino
5 months ago
For this type of question, I'd focus on practical, proven methods to improve receivables collection. Offering discounts and charging late fees are classic approaches. Assessing credit risk upfront is also key. I'll make sure to select those options.
upvoted 0 times
...

Save Cancel