Amazon MLS-C01 Exam - Topic 1 Question 68 Discussion

Actual exam question for Amazon's MLS-C01 exam

Question #: 68
Topic #: 1

A machine learning (ML) specialist must develop a classification model for a financial services company. A domain expert provides the dataset, which is tabular with 10,000 rows and 1,020 features. During exploratory data analysis, the specialist finds no missing values and a small percentage of duplicate rows. There are correlation scores of > 0.9 for 200 feature pairs. The mean value of each feature is similar to its 50th percentile.

Which feature engineering strategy should the ML specialist use with Amazon SageMaker?

AApply dimensionality reduction by using the principal component analysis (PCA) algorithm.

BDrop the features with low correlation scores by using a Jupyter notebook.

CApply anomaly detection by using the Random Cut Forest (RCF) algorithm.

DConcatenate the features with high correlation scores by using a Jupyter notebook.

Show Suggested Answer

Suggested Answer: C

by Lorrie at Dec 27, 2022, 02:21 AM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Toi

4 months ago

No missing values? That's pretty rare in datasets!

upvoted 0 times

...

Arletta

4 months ago

Wait, are we really sure PCA is the best option here?

upvoted 0 times

...

Clarinda

4 months ago

Concatenating high correlation features could lead to overfitting, right?

upvoted 0 times

...

Destiny

4 months ago

I think dropping low correlation features is a better move!

upvoted 0 times

...

Dulce

4 months ago

PCA sounds like a solid choice for reducing dimensions.

upvoted 0 times

...

Gracia

5 months ago

I practiced a similar question where PCA was recommended for datasets with many features. I feel like that could apply here too.

upvoted 0 times

...

Soledad

5 months ago

I think concatenating features with high correlation could lead to multicollinearity issues, but it might also simplify the model. It's a tough call.

upvoted 0 times

...

Emiko

5 months ago

I'm not entirely sure, but dropping low correlation features might not be the best approach since we have a lot of features already.

upvoted 0 times

...

Sol

5 months ago

I remember we discussed PCA in class, especially for reducing dimensionality when features are highly correlated. It seems like a good option here.

upvoted 0 times

...

Elouise

5 months ago

Alright, let me think this through step-by-step. The question is asking about the main contents of the Basle II Proposals, and the options provide different combinations of Roman numerals. I'll need to carefully compare each option to the details in the question.

upvoted 0 times

...

Agustin

5 months ago

Isn't option C similar to one of the practice questions? I think increasing the NAT pool would make sense for handling more addresses.

upvoted 0 times

...

Angella

5 months ago

I think the "number of incremental subscriptions" is the way to go. The goal is to drive new subscriptions, so that metric seems most directly tied to the causal impact of the campaign.

upvoted 0 times

...

Catrice

5 months ago

I'm a little confused on the different router types. Is the firewall router considered a "stateful" router or a "packet-filtering" router? I want to make sure I select the right answer.

upvoted 0 times

...