Microsoft AI-900 Exam - Topic 1 Question 97 Discussion

Actual exam question for Microsoft's AI-900 exam

Question #: 97
Topic #: 1

[All AI-900 Questions]

What are two metrics that you can use to evaluate a regression model? Each correct answer presents a complete solution.

NOTE: Each correct selection is worth one point.

Acoefficient of determination (R2)

BF1 score

Croot mean squared error (RMSE)

Darea under curve (AUC)

Ebalanced accuracy

Show Suggested Answer

Suggested Answer: A, C

A: R-squared (R2), or Coefficient of determination represents the predictive power of the model as a value between -inf and 1.00. 1.00 means there is a perfect fit, and the fit can be arbitrarily poor so the scores can be negative.

C: RMS-loss or Root Mean Squared Error (RMSE) (also called Root Mean Square Deviation, RMSD), measures the difference between values predicted by a model and the values observed from the environment that is being modeled.

https://docs.microsoft.com/en-us/dotnet/machine-learning/resources/metrics

by Vicky at Nov 25, 2025, 10:30 PM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Rickie

17 days ago

Definitely R2, but RMSE is better than AUC here.

upvoted 0 times

...

Willetta

22 days ago

R2 and RMSE are solid choices!

upvoted 0 times

...

Loren

27 days ago

I'm just glad they didn't ask about the Akaike Information Criterion. That one always trips me up!

upvoted 0 times

...

Alaine

1 month ago

B and D are more for classification models, not regression. Gotta read the question carefully!

upvoted 0 times

...

Dudley

1 month ago

I agree with Bulah. Those are the two main metrics I've seen used in my regression projects.

upvoted 0 times

...

Bulah

1 month ago

A and C are the correct answers. R2 and RMSE are commonly used metrics for evaluating regression models.

upvoted 0 times

...

Cherry

2 months ago

I feel like I might confuse RMSE with AUC since they both deal with model evaluation, but I think RMSE is the right choice for regression.

upvoted 0 times

...

Lyndia

2 months ago

I practiced a similar question where R2 and RMSE were the correct answers. I hope that applies here too!

upvoted 0 times

...

Malcolm

2 months ago

I think RMSE is definitely one of the metrics, but I can't recall if R2 is the other one or if there's something else I should consider.

upvoted 0 times

...

Daniel

2 months ago

I remember studying R2 as a key metric for regression, but I'm not entirely sure about the second one. Was it RMSE or something else?

upvoted 0 times

...

Judy

2 months ago

Ugh, I'm drawing a blank here. I know R2 is important, but the other options are throwing me off. I guess I'll just go with R2 and RMSE since those seem like the safest choices.

upvoted 0 times

...

Refugia

2 months ago

Hmm, let me think. R2 for sure, that's a no-brainer. But the other one... I'm torn between RMSE and AUC. I'll hedge my bets and go with R2 and RMSE.

upvoted 0 times

...

Rolande

3 months ago

Okay, I've got this. R2 and RMSE are definitely the way to go. Those are the go-to regression model metrics that we covered in class. I feel pretty confident about this one.

upvoted 0 times

...

Rasheeda

3 months ago

I think R2 and RMSE are the best choices.

upvoted 0 times

...

Yvonne

3 months ago

Haha, I almost picked E just because it sounds fancy. Balanced accuracy is for binary classification, not regression.

upvoted 0 times

...

Kent

4 months ago

Oof, I'm a bit unsure on this one. I know R2 is important, but I'm not totally sure about the other options. Maybe I'll just go with R2 and RMSE to play it safe.

upvoted 0 times

...

Sheridan

4 months ago

Hmm, this seems straightforward. I'd go with R2 and RMSE - those are the classic regression model evaluation metrics, right?

upvoted 0 times

Cheryl

3 months ago

I agree, R2 and RMSE are definitely the go-to metrics.

upvoted 0 times

...

Rolande

3 months ago

Yes! R2 shows how well the model fits the data.

upvoted 0 times

...