Microsoft DP-100 Exam - Topic 1 Question 21 Discussion

Actual exam question for Microsoft's DP-100 exam

Question #: 21
Topic #: 1

You develop and train a machine learning model to predict fraudulent transactions for a hotel booking website.

Traffic to the site varies considerably. The site experiences heavy traffic on Monday and Friday and much lower traffic on other days. Holidays are also high web traffic days. You need to deploy the model as an Azure Machine Learning real-time web service endpoint on compute that can dynamically scale up and down to support demand. Which deployment compute option should you use?

Aattached Azure Databricks cluster

BAzure Container Instance (ACI)

CAzure Kubernetes Service (AKS) inference cluster

DAzure Machine Learning Compute Instance

Eattached virtual machine in a different region

Show Suggested Answer

Suggested Answer: D

Azure Machine Learning compute cluster is a managed-compute infrastructure that allows you to easily create a single or multi-node compute. The compute is created within your workspace region as a resource that can be shared with other users in your workspace. The compute scales up automatically when a job is submitted, and can be put in an Azure Virtual Network.

https://docs.microsoft.com/en-us/azure/machine-learning/how-to-create-attach-compute-sdk

by Viola at May 08, 2022, 03:17 AM

Limited Time Offer

25%

Off

Get Premium DP-100 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Jeannetta

4 months ago

ACI is good for low traffic, but AKS is better for this scenario.

upvoted 0 times

...

Adelle

4 months ago

Not sure about AKS, sounds complicated for real-time.

upvoted 0 times

...

Lucy

4 months ago

Wait, can ACI really handle that much traffic?

upvoted 0 times

...

Emelda

5 months ago

Definitely AKS! It handles traffic spikes well.

upvoted 0 times

...

Melinda

5 months ago

I think Azure Kubernetes Service (AKS) is the best choice for scaling.

upvoted 0 times

...

Leah

5 months ago

I thought Azure Machine Learning Compute Instance was more for development rather than production. Not sure if it can handle the scaling needed here.

upvoted 0 times

...

Rikki

5 months ago

I feel like we practiced a question similar to this, and AKS was the preferred option for handling high demand.

upvoted 0 times

...

Reena

5 months ago

I'm not entirely sure, but I think ACI could work too since it’s easier to set up for smaller workloads.

upvoted 0 times

...

Anabel

5 months ago

I remember we discussed that AKS is great for scaling, especially with fluctuating traffic patterns. It might be the right choice here.

upvoted 0 times

...

Virgie

5 months ago

I'm a bit confused by this question. What exactly is the difference between practical and statistical significance? I feel like I learned this in class, but I'm drawing a blank right now. I'll have to review my notes before answering.

upvoted 0 times

...

Velda

5 months ago

Hmm, I'm a little confused on the timeline here. We start with 1,000 employees, then there's a 20% reduction, and then a 20% increase. I'll need to work through the math step-by-step to make sure I get the right answer.

upvoted 0 times

...

Jin

5 months ago

Ah, I see. Using the schema describe calls to check the user's access seems like a good approach, but it might be overkill for this scenario.

upvoted 0 times

...

Elsa

5 months ago

I remember that injections are things like spending that adds to the economy, right? So maybe exports and government spending are two of them?

upvoted 0 times

...