A company is training an Al model using a custom table to determine the amount of time it takes to deliver a package based on several key fields.The testing data used to train the model is used for all training and regression testing scenarios and is considered complete data.The trained model predicts a 2 percent variance between the estimated delivery time and the actual delivery time of packages.The executive sponsors reject the model because the actual variance is at 15 percent.You need to address the sponsors' concernWhat should you do?

Microsoft PL-200 Exam - Topic 2 Question 107 Discussion

Actual exam question for Microsoft's PL-200 exam

Question #: 107
Topic #: 2

A company is training an Al model using a custom table to determine the amount of time it takes to deliver a package based on several key fields.

The testing data used to train the model is used for all training and regression testing scenarios and is considered complete dat

The trained model predicts a 2 percent variance between the estimated delivery time and the actual delivery time of packages.

The executive sponsors reject the model because the actual variance is at 15 percent.

You need to address the sponsors' concern

What should you do?

AReduce the size of the data used within the model.

Bincrease the size of the data used with the model.

CUse sample training data from Microsoft

DReplace the training data with real-world data.

Show Suggested Answer

Suggested Answer: D

Note: Start using AI Builder with sample data

Don't have any data of your own to create a model? No problem! We've got you covered.

Sample data is available for several AI Builder model types, together with instructions for working with the sample data.

by Tracey at Mar 05, 2026, 05:52 AM

Limited Time Offer

25%

Off

Get Premium PL-200 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Latricia

15 days ago

15% variance? That's a huge gap!

upvoted 0 times

...

Maurine

21 days ago

I think increasing the data size could help.

upvoted 0 times

...

Susana

26 days ago

The model's prediction variance is way off!

upvoted 0 times

...

Gilma

1 month ago

Replacing with real-world data sounds risky, not sure about that.

upvoted 0 times

...

Tracie

1 month ago

Increasing the data size might help improve accuracy.

upvoted 0 times

...

Stefan

1 month ago

Wait, how did they even come up with that 2% figure?

upvoted 0 times

...

Carline

2 months ago

Totally agree, 2% vs 15% is a huge gap!

upvoted 0 times

...

Carmen

2 months ago

The model's predicted variance is way off from reality.

upvoted 0 times

...

Eleonore

2 months ago

I feel like using sample training data from Microsoft could be risky since it might not reflect our specific delivery scenarios.

upvoted 0 times

...

Lizbeth

2 months ago

Reducing the data size seems counterintuitive, but I can't recall why that might be a bad idea.

upvoted 0 times

...

Tiffiny

2 months ago

I think we did a practice question where using real-world data made a significant difference in the model's performance. That might be the right choice.

upvoted 0 times

...

Jackie

2 months ago

I remember we discussed how increasing the size of the data could help improve model accuracy, but I'm not sure if that's the best option here.

upvoted 0 times

...