Amazon MLS-C01 Exam - Topic 2 Question 119 Discussion

Actual exam question for Amazon's MLS-C01 exam

Question #: 119
Topic #: 2

[Modeling]

A company sells thousands of products on a public website and wants to automatically identify products with potential durability problems. The company has 1.000 reviews with date, star rating, review text, review summary, and customer email fields, but many reviews are incomplete and have empty fields. Each review has already been labeled with the correct durability result.

A machine learning specialist must train a model to identify reviews expressing concerns over product durability. The first model needs to be trained and ready to review in 2 days.

What is the MOST direct approach to solve this problem within 2 days?

ATrain a custom classifier by using Amazon Comprehend.

BBuild a recurrent neural network (RNN) in Amazon SageMaker by using Gluon and Apache MXNet.

CTrain a built-in BlazingText model using Word2Vec mode in Amazon SageMaker.

DUse a built-in seq2seq model in Amazon SageMaker.

Show Suggested Answer

Suggested Answer: A

by Lavina at Jul 14, 2025, 12:35 PM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Annice

3 months ago

Wait, can we really train a model in just 2 days?

upvoted 0 times

...

Quentin

3 months ago

Custom classifiers can be hit or miss, though.

upvoted 0 times

...

Laila

3 months ago

Definitely go with BlazingText, it’s the best option here!

upvoted 0 times

...

Alayna

4 months ago

I think an RNN might be overkill for this.

upvoted 0 times

...

Charisse

4 months ago

BlazingText is super fast for text classification!

upvoted 0 times

...

Margurite

4 months ago

BlazingText sounds familiar; I recall it being efficient for text data. It might be the quickest way to get results.

upvoted 0 times

...

Jess

4 months ago

I think we practiced something similar with RNNs, but I'm worried about the time it takes to train them.

upvoted 0 times

...

Reid

4 months ago

I'm not sure if Amazon Comprehend is the best choice here, but it seems like a quick option to get started.

upvoted 0 times

...

Olene

5 months ago

I remember we discussed using pre-trained models for text classification, which might save time.

upvoted 0 times

...

Hobert

5 months ago

Hmm, I'm not sure a seq2seq model in option D is the right fit for this problem. It seems like overkill when we just need to classify the reviews as expressing durability concerns or not. I'd probably go with option A or C for the most direct approach.

upvoted 0 times

...

Olen

5 months ago

Given the tight timeline of 2 days, I think option C using the built-in BlazingText model in Amazon SageMaker would be the fastest way to get a working model. The Word2Vec mode should be able to handle the text data effectively.

upvoted 0 times

...

Amber

5 months ago

I'm a bit unsure about the best approach here. The data has some missing fields, so I'm not sure if a simple classifier would work well. Option B with a recurrent neural network might be a better fit to handle the unstructured text data.

upvoted 0 times

...

Erick

5 months ago

This seems like a straightforward text classification problem, so I think option A using Amazon Comprehend would be the most direct approach to get a model up and running quickly.

upvoted 0 times

...

Candida

7 months ago

If I were the machine learning specialist, I'd be tempted to just throw a coin to decide the answer. But hey, at least they're not asking us to build a self-driving car in a weekend!

upvoted 0 times

...

Leonida

7 months ago

Haha, the company better hope their products are more durable than this machine learning model they're building in 2 days! Gotta love those tight deadlines.

upvoted 0 times

Shalon

6 months ago

D: Use a built-in seq2seq model in Amazon SageMaker.

upvoted 0 times

...

Jose

6 months ago

C: Train a built-in BlazingText model using Word2Vec mode in Amazon SageMaker.

upvoted 0 times

...

Amie

6 months ago

B: Build a recurrent neural network (RNN) in Amazon SageMaker by using Gluon and Apache MXNet.

upvoted 0 times

...

Dominque

6 months ago

A: Train a custom classifier by using Amazon Comprehend.

upvoted 0 times

...

Merilyn

8 months ago

I'm not sure if a seq2seq model is the best fit for this task. It's typically used for tasks like machine translation, not sentiment analysis. I think the BlazingText model is the way to go here.

upvoted 0 times

Becky

6 months ago

I see your point about the seq2seq model not being the best fit. The BlazingText model does seem like a more suitable choice for this specific problem.

upvoted 0 times

...

Carlton

7 months ago

I think using Amazon Comprehend to train a custom classifier could also be a good option for quickly identifying product durability concerns.

upvoted 0 times

...

Linsey

7 months ago

I agree, the BlazingText model using Word2Vec mode seems like the most appropriate choice for this task.

upvoted 0 times

...

Darnell

8 months ago

I see the rationale behind using Amazon Comprehend, but I think training a built-in BlazingText model in Amazon SageMaker could also be a quick and effective solution.

upvoted 0 times

...

Buck

8 months ago

I would go with building a recurrent neural network in Amazon SageMaker using Gluon and Apache MXNet for more customization.

upvoted 0 times

...

Dante

8 months ago

The BlazingText model in Amazon SageMaker seems like the quickest and most direct approach to solve this problem within the 2-day timeline. It's a built-in model, so it should be faster to train than building a custom RNN.

upvoted 0 times