Google Professional Data Engineer Exam - Topic 4 Question 5 Discussion

Actual exam question for Google's Professional Data Engineer exam

Question #: 5
Topic #: 4

[All Professional Data Engineer Questions]

You want to use a database of information about tissue samples to classify future tissue samples as either normal or mutated. You are evaluating an unsupervised anomaly detection method for classifying the tissue samples. Which two characteristic support this method? (Choose two.)

AThere are very few occurrences of mutations relative to normal samples.

BThere are roughly equal occurrences of both normal and mutated samples in the database.

CYou expect future mutations to have different features from the mutated samples in the database.

DYou expect future mutations to have similar features to the mutated samples in the database.

EYou already have labels for which samples are mutated and which are normal in the database.

Show Suggested Answer

Suggested Answer: B, C

by Avery at May 09, 2022, 09:25 AM

Limited Time Offer

25%

Off

Get Premium Professional Data Engineer Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Corazon

4 months ago

D seems off to me, mutations should vary!

upvoted 0 times

...

Xuan

4 months ago

Wait, E is a no-go for unsupervised methods, right?

upvoted 0 times

...

Raina

4 months ago

C makes sense, right? Future mutations might differ.

upvoted 0 times

...

Jaclyn

4 months ago

I think B could work too, but not sure.

upvoted 0 times

...

Joana

5 months ago

A is definitely one of them!

upvoted 0 times

...

Lashawn

5 months ago

I think A and D might be the right answers. A is definitely about the rarity of mutations, but I'm not sure if D is correct since it seems like it contradicts the idea of anomalies.

upvoted 0 times

...

Romana

5 months ago

I feel like C could be a good choice since we might expect new mutations to differ from known ones. D is tricky though; I can't quite recall how that fits in.

upvoted 0 times

...

Arlyne

5 months ago

I remember practicing a question where we discussed the importance of having imbalanced data for anomaly detection, so I feel confident about A. But B seems off to me.

upvoted 0 times

...

Nobuko

5 months ago

I think option A makes sense because if mutations are rare, it aligns with how anomaly detection works. But I'm not sure about the second choice.

upvoted 0 times

...

Teddy

5 months ago

I'm pretty sure the best type of evidence is direct evidence, since that's the most reliable and convincing kind.

upvoted 0 times

...

Carla

5 months ago

Okay, let's see. The Address Book is usually used to store contact information, so I'm guessing Tax ID and maybe Default Document Type could be in there. But I'm not sure about the other options.

upvoted 0 times

...

Raymon

5 months ago

I'm confident Email-to-Case is the way to go here. It's specifically designed to handle email traffic within a company's firewall, which is exactly what the question is asking for.

upvoted 0 times

...

Catrice

5 months ago

Okay, let me think this through. A Personal queue is for individual users, and a Private queue is for a specific team. Since we need to assign teams, I think the Business unit queue is the way to go.

upvoted 0 times

...