Google Professional Machine Learning Engineer Exam - Topic 2 Question 6 Discussion

Actual exam question for Google's Professional Machine Learning Engineer exam

Question #: 6
Topic #: 2

[All Professional Machine Learning Engineer Questions]

Your organization's call center has asked you to develop a model that analyzes customer sentiments in each call. The call center receives over one million calls daily, and data is stored in Cloud Storage. The data collected must not leave the region in which the call originated, and no Personally Identifiable Information (Pll) can be stored or analyzed. The data science team has a third-party tool for visualization and access which requires a SQL ANSI-2011 compliant interface. You need to select components for data processing and for analytics. How should the data pipeline be designed?

A1 = Dataflow, 2 = BigQuery

B1 = Pub/Sub, 2 = Datastore

C1 = Dataflow, 2 = Cloud SQL

D1 = Cloud Function, 2 = Cloud SQL

Show Suggested Answer

Suggested Answer: B

by Kimberlie at May 04, 2022, 09:26 PM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Clorinda

10 months ago

Totally agree with Yasuko, BigQuery is perfect for analytics!

upvoted 0 times

...

Kent

10 months ago

Wait, no PII can be stored? How do they analyze sentiments then?

upvoted 0 times

...

Ming

11 months ago

Cloud SQL? Really? Not sure that fits the scale here.

upvoted 0 times

...

Adaline

11 months ago

I think Pub/Sub and Datastore would be better for real-time processing.

upvoted 0 times

...

Yasuko

11 months ago

Dataflow and BigQuery seem like a solid combo for this.

upvoted 0 times

...

Cecilia

11 months ago

I feel like using Pub/Sub could help with real-time data ingestion, but I'm uncertain if it integrates well with the visualization tool mentioned.

upvoted 0 times

...

Corrina

11 months ago

I practiced a similar question where we had to choose between Cloud SQL and Datastore, but I can't recall which one is better for handling large volumes of data like this.

upvoted 0 times

...

Annice

11 months ago

I think BigQuery might be the right choice for analytics since it supports SQL queries, but I need to double-check if it meets the regional data requirements.

upvoted 0 times

...

Ty

11 months ago

I remember that Dataflow is great for processing large datasets, but I'm not entirely sure if it's the best fit for this specific scenario.

upvoted 0 times

...

Mari

11 months ago

Okay, I think I've got a plan. I'll need to create a managed identity for DF1, grant that identity access to the password in Key Vault, and then use that identity to connect DF1 to SQL1. Hopefully, that will meet the least privilege requirement.

upvoted 0 times

...

Huey

11 months ago

Ah, I think I've got it. Since symmetric encryption is meant for short-term use, the prolonged use of the same key must have led to its compromise somehow. I'll explore that angle.

upvoted 0 times

...

Veronique

11 months ago

I'm a bit confused by this question. All of these factors seem important when deciding whether to replace equipment. I'll have to review my notes and try to remember the key considerations.

upvoted 0 times

...

Kris

11 months ago

Hmm, I'm a little unsure about this one. The wording of the question and answer choices is a bit technical. I'll need to think through each option carefully to make sure I don't miss any important details.

upvoted 0 times

...