Amazon Exam MLS-C01 Topic 5 Question 76 Discussion

Actual exam question for Amazon's MLS-C01 exam

Question #: 76
Topic #: 5

A company deployed a machine learning (ML) model on the company website to predict real estate prices. Several months after deployment, an ML engineer notices that the accuracy of the model has gradually decreased.

The ML engineer needs to improve the accuracy of the model. The engineer also needs to receive notifications for any future performance issues.

Which solution will meet these requirements?

APerform incremental training to update the model. Activate Amazon SageMaker Model Monitor to detect model performance issues and to send notifications.

BUse Amazon SageMaker Model Governance. Configure Model Governance to automatically adjust model hyper para meters. Create a performance threshold alarm in Amazon CloudWatch to send notifications.

CUse Amazon SageMaker Debugger with appropriate thresholds. Configure Debugger to send Amazon CloudWatch alarms to alert the team Retrain the model by using only data from the previous several months.

DUse only data from the previous several months to perform incremental training to update the model. Use Amazon SageMaker Model Monitor to detect model performance issues and to send notifications.

Show Suggested Answer

Suggested Answer: B, D

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

by Jutta at Jul 09, 2023, 12:57 PM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Delisa

1 months ago

So the model's performance is slipping, huh? I guess you could say it's having a 'housing crisis' of its own. Time to whip it back into shape before it ends up living in a cardboard box!

upvoted 0 times

...

Aileen

1 months ago

D is the clear winner for me. Using recent data for incremental training is a no-brainer, and SageMaker Model Monitor will keep an eye on things. Plus, it's the most straightforward option - no need to mess with all that fancy governance or debugging stuff.

upvoted 0 times

Shaniqua

5 days ago

Yeah, option D is the most practical and efficient solution for improving accuracy and monitoring the model.

upvoted 0 times

...

Dan

10 days ago

SageMaker Model Monitor will definitely help in keeping track of any performance issues.

upvoted 0 times

...

Dyan

12 days ago

I agree, option D seems like the best choice. Incremental training with recent data is key.

upvoted 0 times

...

Bok

2 months ago

Option C with SageMaker Debugger looks interesting, but I'm not sure about the whole 'retrain with only the last few months of data' part. Seems like we might be losing valuable historical information.

upvoted 0 times

Lennie

2 days ago

Maybe we can combine elements from different options to find a solution that works best for us. Incremental training with Model Monitor could be a good approach.

upvoted 0 times

...

Alexis

6 days ago

I agree, but I also have concerns about retraining the model with only recent data. We might lose valuable insights from historical data.

upvoted 0 times

...

Mitzie

13 days ago

I see your point about Option C, but I think sticking with Option A would be more reliable in this situation.

upvoted 0 times

...

Shad

17 days ago

I agree, Option A seems like a solid solution. It's important to stay updated on the model's performance.

upvoted 0 times

...

Melodie

23 days ago

I think Option A is the best choice. Incremental training can update the model and SageMaker Model Monitor will send notifications for any performance issues.

upvoted 0 times

...

Kallie

24 days ago

Option C with SageMaker Debugger sounds promising. We can set appropriate thresholds and configure it to send alerts through Amazon CloudWatch.

upvoted 0 times

...

Brandee

2 months ago

I like the idea of using Model Governance in option B. Automatically adjusting the hyper parameters could be really helpful, and the CloudWatch alarms will give us proactive alerts. That's a clever approach.

upvoted 0 times

Bernardo

15 days ago

Yes, having the system automatically adjust hyper parameters and send notifications for performance issues is a great way to maintain model accuracy.

upvoted 0 times

...

Tijuana

18 days ago

Using Model Governance to adjust hyper parameters automatically is a smart move. It can save time and improve accuracy.

upvoted 0 times

...

Sherita

1 months ago

I agree, proactive alerts from CloudWatch alarms would be very useful in detecting performance issues early.

upvoted 0 times

...

Barb

2 months ago

Option B sounds like a good choice. Automatically adjusting hyper parameters could help improve accuracy.

upvoted 0 times

...

Glendora

2 months ago

Hmm, that's a good point. Maybe option C is indeed a more comprehensive solution for improving accuracy and receiving notifications.

upvoted 0 times

...

Jovita

2 months ago

I disagree, I believe option C is better. Debugger with appropriate thresholds can alert the team and retraining the model is crucial.

upvoted 0 times

...

Rozella

2 months ago

Option A seems like the way to go. Incremental training is a great way to keep the model up-to-date, and SageMaker Model Monitor will make it easy to catch any performance issues. Sounds like a solid solution.

upvoted 0 times

Rolande

1 months ago

I agree, Option A sounds like a solid solution. It's important to stay on top of model performance to ensure accurate predictions.

upvoted 0 times

...

Levi

1 months ago

Option A seems like the best choice. Incremental training will help keep the model accurate, and Model Monitor will alert us to any issues.

upvoted 0 times

...

Glendora

2 months ago

I think option A is the best choice. Incremental training can help improve accuracy and Model Monitor can send notifications.

upvoted 0 times

...

Lyla

2 months ago

Hmm, that's a good point. Maybe a combination of both options A and C could be the most effective solution.

upvoted 0 times

...

Corrinne

2 months ago

I disagree, I believe option C is better. Debugger with appropriate thresholds can help detect issues and send alerts for retraining.

upvoted 0 times

...

Lyla

3 months ago

I think option A is the best solution. Incremental training can help improve accuracy and Model Monitor can send notifications.

upvoted 0 times

...