Databricks Machine Learning Professional Exam - Topic 1 Question 4 Discussion

Actual exam question for Databricks's Databricks Machine Learning Professional exam

Question #: 4
Topic #: 1

[All Databricks Machine Learning Professional Questions]

A machine learning engineer needs to deliver predictions of a machine learning model in real-time. However, the feature values needed for computing the predictions are available one week before the query time.

Which of the following is a benefit of using a batch serving deployment in this scenario rather than a real-time serving deployment where predictions are computed at query time?

ABatch serving has built-in capabilities in Databricks Machine Learning

BThere is no advantage to using batch serving deployments over real-time serving deployments

CComputing predictions in real-time provides more up-to-date results

DTesting is not possible in real-time serving deployments

EQuerying stored predictions can be faster than computing predictions in real-time

Show Suggested Answer

Suggested Answer: A

by Nan at Dec 12, 2023, 03:41 AM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Merlyn

6 months ago

I agree, testing can be tricky in real-time setups.

upvoted 0 times

...

Genevive

6 months ago

Querying stored predictions is definitely faster!

upvoted 0 times

...

Willow

6 months ago

Wait, isn't real-time serving more flexible?

upvoted 0 times

...

Aileen

7 months ago

I think real-time is always better for accuracy.

upvoted 0 times

...

Lazaro

7 months ago

Batch serving can handle large datasets efficiently!

upvoted 0 times

...

Talia

7 months ago

I feel like there was something about testing being easier with batch deployments, but I'm not completely confident in that.

upvoted 0 times

...

Mozell

7 months ago

I think we had a practice question about the advantages of batch vs. real-time, but I can't recall the specifics.

upvoted 0 times

...

Margurite

7 months ago

I'm not entirely sure, but I feel like querying stored predictions could be faster than computing them on the fly.

upvoted 0 times

...

Marcos

8 months ago

I remember discussing batch serving in class, and I think it can be more efficient when you have data ready in advance.

upvoted 0 times

...

Gilma

8 months ago

Interesting. I wonder if there are any other benefits to batch serving that I'm missing. I'll make sure to review all the options thoroughly.

upvoted 0 times

...

Monroe

8 months ago

I've got this! Batch serving can be faster since the predictions are pre-computed. That could be a big advantage in this scenario.

upvoted 0 times

...

Corazon

8 months ago

Wait, I'm a bit confused. Isn't real-time serving supposed to be more up-to-date? I'll need to re-read the question carefully.

upvoted 0 times

...

Julie

8 months ago

Okay, let's see. If the feature values are available a week in advance, then batch serving could be faster than real-time. I'll make sure to consider that.

upvoted 0 times

...

Misty

8 months ago

Hmm, this seems like a tricky one. I'll need to think through the trade-offs between batch and real-time serving.

upvoted 0 times

...

Adelaide

8 months ago

Hmm, I'm not totally sure about this one. I'll need to double-check the message options to make sure I'm doing it correctly.

upvoted 0 times

...

Shaniqua

8 months ago

Okay, let's see. The key is to identify the option that does not align with the information provided in the question. I'll need to weigh each answer carefully.

upvoted 0 times

...