Google Exam Professional Data Engineer Topic 3 Question 71 Discussion

Actual exam question for Google's Professional Data Engineer exam

Question #: 71
Topic #: 3

[All Professional Data Engineer Questions]

You are developing an application that uses a recommendation engine on Google Cloud. Your solution should display new videos to customers based on past views. Your solution needs to generate labels for the entities in videos that the customer has viewed. Your design must be able to provide very fast filtering suggestions based on data from other customer preferences on several TB of dat

a. What should you do?

ABuild and train a complex classification model with Spark MLlib to generate labels and filter the results.
Deploy the models using Cloud Dataproc. Call the model from your application.

BBuild and train a classification model with Spark MLlib to generate labels. Build and train a second
classification model with Spark MLlib to filter results to match customer preferences. Deploy the models
using Cloud Dataproc. Call the models from your application.

CBuild an application that calls the Cloud Video Intelligence API to generate labels. Store data in Cloud
Bigtable, and filter the predicted labels to match the user's viewing history to generate preferences.

DBuild an application that calls the Cloud Video Intelligence API to generate labels. Store data in Cloud
SQL, and join and filter the predicted labels to match the user's viewing history to generate preferences.

Show Suggested Answer

Suggested Answer: C

by Lucy at Oct 09, 2023, 05:21 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

Audra

1 months ago

As a video enthusiast, I'd love to see a recommendation engine that can keep up with my binge-watching habits! Option C sounds like it would be a 'reel' winner.

upvoted 0 times

Louvenia

Option C sounds like a great choice for generating labels and filtering suggestions based on customer preferences.

upvoted 0 times

...

Stephanie

2 months ago

Hmm, I'm not sure I'd want to build a complex Spark MLlib model just for this task. The Cloud Video Intelligence API in Option C or D looks like a more efficient solution to me.

upvoted 0 times

Donette

6 days ago

Yeah, I think using the Cloud Video Intelligence API in Option C or D would be the way to go for fast filtering suggestions.

upvoted 0 times

...

Salome

7 days ago

I agree, Option D also seems like a good option. Storing data in Cloud SQL could be useful.

upvoted 0 times

...

Ocie

15 days ago

Yeah, building and training multiple models in Option B might be overkill. The Cloud Video Intelligence API sounds simpler.

upvoted 0 times

...

Quentin

16 days ago

Option C sounds like a good choice. Using the Cloud Video Intelligence API seems efficient.

upvoted 0 times

...

Frederic

18 days ago

I agree, Option D also seems like a good option. Storing data in Cloud SQL could be useful.

upvoted 0 times

...

Talia

27 days ago

Option C sounds like a good choice. Using the Cloud Video Intelligence API seems efficient.

upvoted 0 times

...

Fernanda

2 months ago

Option D seems like a good choice if you're already familiar with Cloud SQL. The simplicity of storing data in a relational database and joining the labels with user history could be a straightforward approach.

upvoted 0 times

Tonette

17 days ago

That's true, combining the API for labels with Cloud SQL for filtering could be a powerful combination.

upvoted 0 times

...

Rashida

20 days ago

But wouldn't using the Cloud Video Intelligence API to generate labels be more accurate?

upvoted 0 times

...

Nina

21 days ago

I agree, using Cloud SQL for storing data and joining labels with user history sounds efficient.

upvoted 0 times

...

Kenia

1 months ago

Option D seems like a good choice if you're already familiar with Cloud SQL.

upvoted 0 times

...

Joana

2 months ago

I'm leaning towards Option B. Having two separate models, one for generating labels and one for filtering, could provide more flexibility and control over the recommendation process.

upvoted 0 times

Bernardine

2 months ago

I agree, Option B seems like it would give us more control over the recommendation process.

upvoted 0 times

...

Frederica

2 months ago

Option B sounds like a good choice. Having separate models for generating labels and filtering could be beneficial.

upvoted 0 times

...

Patrick

2 months ago

That's a good point, but I still think option A is more straightforward and easier to implement.

upvoted 0 times

...

Lynelle

2 months ago

I disagree, I believe option B is better. Having two classification models for labeling and filtering can provide more accurate results.

upvoted 0 times

...

Galen

2 months ago

Option C looks like the most efficient and scalable solution. Using the Cloud Video Intelligence API and Cloud Bigtable seems like a great way to handle the large amounts of data and provide fast filtering capabilities.

upvoted 0 times

Mary

29 days ago

Yes, using Cloud Bigtable for storing data and filtering predicted labels based on user viewing history is a smart choice for this recommendation engine application.

upvoted 0 times

...

Arthur

1 months ago

It's important to have fast filtering suggestions based on customer preferences, and Cloud Bigtable can definitely help with that.

upvoted 0 times

...

Jeffrey

1 months ago

I agree, Cloud Video Intelligence API can help generate accurate labels for the videos, and Cloud Bigtable can handle the massive amount of data efficiently.

upvoted 0 times

...

Colene

1 months ago

upvoted 0 times

...

Patrick

2 months ago

I think option A is the best choice. Using Spark MLlib for classification and Cloud Dataproc for deployment seems efficient.

upvoted 0 times

...