Amazon MLS-C01 Exam - Topic 10 Question 78 Discussion

Actual exam question for Amazon's MLS-C01 exam

Question #: 78
Topic #: 10

A company offers an online shopping service to its customers. The company wants to enhance the site's security by requesting additional information when customers access the site from locations that are different from their normal location. The company wants to update the process to call a machine learning (ML) model to determine when additional information should be requested.

The company has several terabytes of data from its existing ecommerce web servers containing the source IP addresses for each request made to the web server. For authenticated requests, the records also contain the login name of the requesting user.

Which approach should an ML specialist take to implement the new security feature in the web application?

AUse Amazon SageMaker Ground Truth to label each record as either a successful or failed access attempt. Use Amazon SageMaker to train a binary classification model using the factorization machines (FM) algorithm.

BUse Amazon SageMaker to train a model using the IP Insights algorithm. Schedule updates and retraining of the model using new log data nightly.

CUse Amazon SageMaker Ground Truth to label each record as either a successful or failed access attempt. Use Amazon SageMaker to train a binary classification model using the IP Insights algorithm.

DUse Amazon SageMaker to train a model using the Object2Vec algorithm. Schedule updates and retraining of the model using new log data nightly.

Show Suggested Answer

Suggested Answer: B, D

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

by Willow at Aug 07, 2023, 12:43 AM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Teddy

3 months ago

Wait, can ML really handle this kind of security issue effectively?

upvoted 0 times

...

Paul

3 months ago

Totally agree with B, nightly updates are crucial!

upvoted 0 times

...

Nieves

4 months ago

Not sure about the effectiveness of the Object2Vec algorithm for this.

upvoted 0 times

...

King

4 months ago

I think C is better since it uses a binary classification model.

upvoted 0 times

...

Viola

4 months ago

Option B seems solid for IP-based insights.

upvoted 0 times

...

Alease

4 months ago

I vaguely recall that factorization machines are good for sparse data, but I'm not confident if they apply to this specific use case with IP addresses.

upvoted 0 times

...

Yuette

4 months ago

I feel like we practiced a similar question about choosing algorithms based on data types, but I can't remember if binary classification is the right approach for this scenario.

upvoted 0 times

...

Justa

5 months ago

I think using the IP Insights algorithm makes sense since it focuses on user behavior, but I can't recall if it requires labeled data or not.

upvoted 0 times

...

Rasheeda

5 months ago

I remember we discussed the importance of labeling data for supervised learning, but I'm not sure if Ground Truth is the best choice here.

upvoted 0 times

...

Aimee

5 months ago

This seems like a straightforward skills assessment question. I'll need to carefully analyze the data to determine the best option to fill the skill gaps.

upvoted 0 times

...

Carissa

5 months ago

I'm leaning towards A as well. It seems like the most logical way to modify the code and restart the session. The other options don't seem as clear or straightforward to me.

upvoted 0 times

...

Miles

5 months ago

I was practicing similar questions, and I remember that consumer protection statutes don't always cover CAM services. So maybe C is worth considering?

upvoted 0 times

...

Ligia

10 months ago

Wait, we're talking about security, not online shopping recommendations. Can we get a model that just blocks all the hackers and leaves the good customers alone? Simple is sometimes best, you know.

upvoted 0 times

Leatha

8 months ago

C) Use Amazon SageMaker Ground Truth to label each record as either a successful or failed access attempt. Use Amazon SageMaker to train a binary classification model using the IP Insights algorithm.

upvoted 0 times

...

Galen

8 months ago

B) Use Amazon SageMaker to train a model using the IP Insights algorithm. Schedule updates and retraining of the model using new log data nightly.

upvoted 0 times

...

Juliana

9 months ago

A) Use Amazon SageMaker Ground Truth to label each record as either a successful or failed access attempt. Use Amazon SageMaker to train a binary classification model using the factorization machines (FM) algorithm.

upvoted 0 times

...

Xochitl

10 months ago

Option D with Object2Vec? Sounds like someone is trying to show off their machine learning chops. Let's keep it simple, folks. I'm with Louvenia on Option B.

upvoted 0 times

...

Markus

10 months ago

All these options sound pretty technical, but I'm leaning towards Option B. Automated retraining is key to keeping the model up-to-date. Now, where's the 'cheat sheet' when you need it?

upvoted 0 times

...

Jonell

10 months ago

Option C looks promising, but I wonder if the Ground Truth labeling process will be time-consuming and labor-intensive. Hmm, something to consider.

upvoted 0 times

Anglea

8 months ago

Yes, that approach seems efficient. It's important to have accurate labeling for the ML model to make the right decisions for enhancing security.

upvoted 0 times

...

Alease

8 months ago

I think using Amazon SageMaker Ground Truth to label each record as successful or failed access attempts is a good idea. It can help train a binary classification model effectively.

upvoted 0 times

...

Latrice

9 months ago

Option C looks promising, but I wonder if the Ground Truth labeling process will be time-consuming and labor-intensive. Hmm, something to consider.

upvoted 0 times

...

Louvenia

10 months ago

I think Option B is the way to go. Using the IP Insights algorithm with scheduled updates and retraining is a smart approach to adapt to changes in user behavior over time.

upvoted 0 times

Chantell

10 months ago

I think Option A could also work well. Using the factorization machines algorithm for binary classification could provide accurate results for identifying potential security risks.

upvoted 0 times

...

Nettie

10 months ago

I agree, Option B seems like a practical choice. Updating and retraining the model regularly will help keep the security measures up to date.

upvoted 0 times

...

Arthur

11 months ago

That's a good point, but I still think option A is more suitable for this scenario.

upvoted 0 times

...

Audry

11 months ago

I disagree, I believe option C is better as it combines labeling with the IP Insights algorithm for classification.

upvoted 0 times

...

Arthur

11 months ago

I think option A is the best approach because it uses the factorization machines algorithm for binary classification.

upvoted 0 times

...