Deal of The Day! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25

- Free Preparation Discussions

Microsoft AI-900 Exam - Topic 4 Question 98 Discussion

Actual exam question for Microsoft's AI-900 exam

Question #: 98
Topic #: 4

[All AI-900 Questions]

During the process of Machine Learning, when should you review evaluation metrics?

AAfter you clean the data.

BBefore you train a model.

CBefore you choose the type of model.

DAfter you test a model on the validation data.

Show Suggested Answer

Suggested Answer: D

by Lamar at Jan 05, 2026, 05:16 AM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Vashti

26 days ago

A is important too, but I feel D is crucial after testing.

upvoted 0 times

...

Casie

1 month ago

I lean towards C. Choosing the model type should consider metrics too.

upvoted 0 times

...

Marla

1 month ago

I agree, D makes sense. Evaluation metrics show real performance.

upvoted 0 times

...

Roy

1 month ago

I think D is the best choice. You need to see how the model performs first.

upvoted 0 times

...

Shawna

2 months ago

Metrics matter at every stage, but especially before model selection!

upvoted 0 times

...

Essie

2 months ago

I disagree, it should be reviewed before training too.

upvoted 0 times

...

Tina

2 months ago

Surprised that people don’t mention it after cleaning the data!

upvoted 0 times

...

Daron

2 months ago

I think it’s more important after testing on validation data.

upvoted 0 times

...

Kirby

2 months ago

Definitely before you choose the type of model!

upvoted 0 times

...

Launa

2 months ago

This question is a piece of cake. I could answer it in my sleep!

upvoted 0 times

...

Jennie

3 months ago

D) After you test a model on the validation data. Duh, how else are you gonna know if it's any good?

upvoted 0 times

...

Aileen

3 months ago

A) After you clean the data. Gotta make sure it's all nice and tidy first.

upvoted 0 times

...

Catherin

3 months ago

C) Before you choose the type of model. Helps you pick the right one for the job.

upvoted 0 times

...

Carole

4 months ago

B) Before you train a model. Gotta know what you're aiming for, right?

upvoted 0 times

...

Laine

4 months ago

D) After you test a model on the validation data. That's when you can really see how well it's performing.

upvoted 0 times

...

Helaine

4 months ago

I practiced a question similar to this, and I think the right time is after cleaning the data. But I could be mixing it up with another concept!

upvoted 0 times

...

Kassandra

4 months ago

I feel like we should consider metrics before choosing the type of model. Different models might require different evaluation criteria, but I can't recall exactly.

upvoted 0 times

...

Emelda

4 months ago

I'm not too sure, but I remember something about checking metrics after testing on validation data. That seems important for understanding performance.

upvoted 0 times

...

Renay

5 months ago

I think we should review evaluation metrics before we train a model, right? It helps to know what we're aiming for.

upvoted 0 times

...

Jonell

5 months ago

Reviewing the metrics at multiple stages seems important - before the model, during training, and after validation. Gotta make sure the model is on the right track.

upvoted 0 times

...

Nan

5 months ago

I'm a bit confused on this one. Is it after cleaning the data or before choosing the model? I'll have to think it through carefully.

upvoted 0 times

...

Charlie

5 months ago

Definitely before training the model. You need to know what you're optimizing for before you start the training process.

upvoted 0 times

...

Jenelle

5 months ago

Hmm, I'm not sure. I guess I'd review the metrics after testing the model on the validation data, to see how well it's performing.

upvoted 0 times

...

Rosalia

5 months ago

I think I'd review the evaluation metrics before choosing the model type. That way I can pick the right model for the task based on the data.

upvoted 0 times

...