Amazon MLS-C01 Exam - Topic 1 Question 72 Discussion

Actual exam question for Amazon's MLS-C01 exam

Question #: 72
Topic #: 1

A university wants to develop a targeted recruitment strategy to increase new student enrollment. A data scientist gathers information about the academic performance history of students. The data scientist wants to use the data to build student profiles. The university will use the profiles to direct resources to recruit students who are likely to enroll in the university.

Which combination of steps should the data scientist take to predict whether a particular student applicant is likely to enroll in the university? (Select TWO)

AUse Amazon SageMaker Ground Truth to sort the data into two groups named 'enrolled' or 'not enrolled.'

BUse a forecasting algorithm to run predictions.

CUse a regression algorithm to run predictions.

DUse a classification algorithm to run predictions

EUse the built-in Amazon SageMaker k-means algorithm to cluster the data into two groups named 'enrolled' or 'not enrolled.'

Show Suggested Answer

Suggested Answer: B, D

https://www.redhat.com/en/topics/devops/what-is-blue-green-deployment

by Bobbye at Mar 25, 2023, 04:10 PM

Limited Time Offer

25%

Off

Get Premium MLS-C01 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Kanisha

4 months ago

I don’t know, using regression seems risky for this type of data.

upvoted 0 times

...

Aron

4 months ago

Totally agree with D! Classification is key here.

upvoted 0 times

...

Catina

4 months ago

Wait, can you really use k-means for this? Seems off.

upvoted 0 times

...

Sherman

5 months ago

I think A is a good choice too, but not sure about E.

upvoted 0 times

...

Fernanda

5 months ago

Definitely B and D for predictions!

upvoted 0 times

...

Isaiah

5 months ago

I feel like clustering with k-means might not be the best approach since we need to predict outcomes, not just group data.

upvoted 0 times

...

Buddy

5 months ago

I practiced a similar question where we had to classify data, and I think using Amazon SageMaker for sorting could be helpful, but I'm not sure if it's the right step.

upvoted 0 times

...

Antonio

5 months ago

I'm not entirely sure, but I remember something about regression being used for continuous outcomes, so it might not be the best fit here.

upvoted 0 times

...

Joanna

5 months ago

I think we should use a classification algorithm to predict enrollment since we're dealing with categories like 'enrolled' or 'not enrolled.'

upvoted 0 times

...

Wei

5 months ago

I vaguely recall something about clustering methods like k-means, but I don't think it fits this scenario since we need to predict enrollment, not just group data. So, E seems off.

upvoted 0 times

...

Vince

5 months ago

I practiced a similar question where we had to classify data into categories. I think using a classification algorithm is definitely the way to go, so D seems solid.

upvoted 0 times

...

Elouise

5 months ago

I'm a bit unsure about the best approach here. I feel like regression could work too, but isn't it more for continuous outcomes? Maybe option C isn't the right fit?

upvoted 0 times

...

Marshall

5 months ago

I remember we discussed the importance of classification algorithms for binary outcomes like enrollment status. I think option D might be a good choice.

upvoted 0 times

...

Frank

5 months ago

Hmm, this looks familiar, but I want to make sure I get the order right. I'll think it through step-by-step.

upvoted 0 times

...

Mollie

5 months ago

Ah, I think I know this one! Participatory design involves users throughout the process, so the answer is likely A - discovery, evaluation, and prototype.

upvoted 0 times

...

Eun

5 months ago

This one seems pretty straightforward. I think the answer is Remote service observation, since that's a common way to monitor calls in a Service Desk.

upvoted 0 times

...

Luis

5 months ago

Wait, is CPR the right acronym here? I'm not totally sure what that stands for in this context.

upvoted 0 times

...

Brigette

10 months ago

I don't know, guys. Using a forecasting algorithm to predict enrollment seems a bit overkill. Why not just use a good old-fashioned classification algorithm and call it a day?

upvoted 0 times

Shad

10 months ago

C: I think using a forecasting algorithm might be too complex for predicting student enrollment.

upvoted 0 times

...

James

10 months ago

B: Yeah, I think using a classification algorithm would be more efficient for this task.

upvoted 0 times

...

Donte

10 months ago

A: I agree, using a classification algorithm would be simpler and more straightforward.

upvoted 0 times

...

Annice

11 months ago

Haha, I can just imagine the data scientist using Amazon SageMaker Ground Truth to manually label each student as 'enrolled' or 'not enrolled'. Talk about a labor-intensive approach!

upvoted 0 times

Barney

9 months ago

Joesph: True, combining different algorithms could give more accurate results.

upvoted 0 times

...

Lindy

9 months ago

User 3: Using a forecasting algorithm could also help predict enrollment.

upvoted 0 times

...

Joesph

9 months ago

User 2: They could also use a classification algorithm to automate the process.

upvoted 0 times

...

Destiny

10 months ago

User 1: Haha, that does sound like a lot of work!

upvoted 0 times

...

Shala

10 months ago

D: Using a forecasting algorithm could also help in predicting enrollment trends.

upvoted 0 times

...

Hershel

10 months ago

C: They could also use Amazon SageMaker k-means algorithm to cluster the data.

upvoted 0 times

...

Lucia

10 months ago

B: Yeah, that would be more efficient than manually labeling each student.

upvoted 0 times

...

Junita

10 months ago

A: I think they should use a classification algorithm to predict enrollment.

upvoted 0 times

...

Hollis

11 months ago

I'm not so sure about that. Shouldn't we be using something like k-means clustering to group the students first before running any predictions? That could give us better insights into the key characteristics of the 'enrolled' and 'not enrolled' groups.

upvoted 0 times

Sabrina

10 months ago

B: Yeah, that makes sense. We can then use a classification algorithm to predict whether a particular student is likely to enroll based on those key characteristics.

upvoted 0 times

...

Johna

10 months ago

A: I think you're right. Using k-means clustering could help us identify important characteristics of the 'enrolled' and 'not enrolled' groups.

upvoted 0 times

...

Mel

11 months ago

I think options C and D are the way to go. Using a regression algorithm to predict enrollment probability and a classification algorithm to directly classify students as 'enrolled' or 'not enrolled' seems like the most logical approach.

upvoted 0 times

...