How to reduce latency for global banking app predictions?

PMLE By islever Editorial Last updated Aug 31, 2026

Short answer

C Deploy the model to Vertex AI private endpoints in the us-central1 and asia-southeast1 regions, and allow the application to choose the appropriate endpoint.

Question

You work for a large bank that serves customers through an application hosted in Google Cloud that is running in the US and Singapore. You have developed a PyTorch model to classify transactions as potentially fraudulent or not. The model is a three-layer perceptron that uses both numerical and categorical features as input, and hashing happens within the model. You deployed the model to the us-central1 region on nl-highcpu-16 machines, and predictions are served in real time. The model's current median response latency is 40 ms. You want to reduce latency, especially in Singapore, where some customers are experiencing the longest delays. What should you do?

Attach an NVIDIA T4 GPU to the machines being used for online inference.
Change the machines being used for online inference to nl-highcpu-32.
Deploy the model to Vertex AI private endpoints in the us-central1 and asia-southeast1 regions, and allow the application to choose the appropriate endpoint. Correct Answer
Create another Vertex AI endpoint in the asia-southeast1 region, and allow the application to choose the appropriate endpoint.

Key Takeaways

This question tests the ability to optimize inference latency through geographical distribution and security compliance, with the trap being overlooking the 'bank' context which necessitates private endpoints over public ones.

To reduce latency for a banking application serving global users, deploying models to Vertex AI private endpoints in multiple regions is the optimal solution. The community agrees that private endpoints address both the geographical latency and the security requirements implied by the banking sector.

Common mistake: Choosing option D is a common mistake because it correctly identifies the need for regional deployment in Singapore but fails to account for the security requirements of a financial institution, making private endpoints the necessary choice.

Expert Analysis

Why the Answer Is Correct

Option C is correct because deploying the model to asia-southeast1 physically places the compute resources closer to Singapore users, drastically reducing network latency. Furthermore, using "private endpoints" ensures that the traffic remains within the secure Google Cloud network, which is a standard best practice for large banks handling sensitive financial data. This solution addresses both the performance bottleneck and the implicit security constraints of the scenario.

Why the Other Options Are Wrong

Option A is incorrect because adding a GPU to a simple three-layer perceptron is unnecessary and expensive, failing to address the network latency issue. Option B is incorrect because upgrading the CPU machine type only marginally improves compute speed and does nothing to reduce the physical distance between Singapore users and the US-based model. Option D is incorrect because, while it solves the latency issue, it ignores the security context of a "large bank" by not mandating private endpoints.

Community Comment Notes

Several commenters highlighted the "bank" keyword as the deciding factor for choosing private endpoints over standard ones. One user noted that banking applications should never access models over the public internet, reinforcing why C is superior to D. Another commenter clarified that the primary bottleneck is network latency, not compute power, which rules out the hardware upgrade options.

Official Reference

These links open the official vendor documentation in a new tab.

Exam Strategy

Always look for industry-specific keywords like 'bank,' 'healthcare,' or 'PII' in exam questions, as they often dictate security requirements such as VPC peering or private endpoints, even if the primary question seems to focus on performance or cost.

Community Votes

62%

38%

62% of anonymous learners picked answer C. Votes are pick records left by other test-takers — they are not the verified answer.

Discussion 9 contributions

Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.

From public community threads 9

guilhermebutzke 👍 9 Answered C

My Answer: C The bottleneck is network latency. So, A: Not Correct: might improve performance, but it's an expensive solution and may not be necessary if the bottleneck is network latency. B: Not Correct: might offer slight improvement, but the primary issue is geographical distance between users and the model. C: CORRECT: This approach leverages the geographical proximity of the endpoints to the users, reducing latency for customers in Singapore without neglecting customers in the US. Additionally, using Vertex AI private endpoints ensures secure and efficient communication between the application and the model. D: Not Correct: it's not the most efficient approach because it does not utilize the existing infrastructure in the us-central1 region, and managing multiple endpoints might introduce additional complexity.
f084277 👍 3 Answered C

You work for a BANK. An application accesses the model and serves predictions to customers. The application is in US and Singapore. The application should never access the model over the public internet. Therefore, private endpoints.
omermahgoub 👍 2 Answered C

Deploying the model to a Vertex AI private endpoint in the Singapore region brings the model closer to users in that region. This significantly reduces network latency for those users compared to accessing the model hosted in us-central1. Allowing the application to choose the appropriate endpoint based on user location (through private endpoints) ensures users access the geographically closest model replica, optimizing latency. Why not D: creating a separate endpoint in Singapore would allow regional deployment, it wouldn't automatically route users to the closest endpoint. You still need additional logic within the application for regional routing, increasing complexity.
inc_dev_ml_001 👍 2 Answered D

I think it's D because C and D should work in the same way, but ensuring the connection through a private endpoint it's not necessary because in the question there's nothing about security or sensitive informations. So the scope for a generic endpoint is "Accessible from anywhere", the scope for a private endpoint is "Accessible only within VPC or private connections". Don't see why to do that, it's only a matter of latency, not a matter of safety.
GuineaPigHunter 👍 2 Answered D

Not sure why I'd choose C over D, my choice is D. Model is already deployed to us-central1 so now it's only a matter of deploying it to asia-southeast1 and letting the app choose the closer endpoint. Why the need for private endpoints and what will happen with the current already deployed model in us-central1?

Show 4 more comments

wences 👍 1 Answered D

I don't have any link to support this other than a simple analysis; if you want the data or process to be low latency, you need to deploy closes where it is required, in this case, to Singapore customers, which reduces latetency addressing the requirement.
devops_bms 👍 1 Answered C

using private endpoints shorten the network path between the model and the client app
shuvs 👍 1 Answered D

I think it is D. C is questionable as why do you need a private endpoint?
uatud3 👍 1 Answered D

I picked D. Sounds like the most logical answer

Reader comments & corrections

No reader corrections yet — spotted an error or have a note? Share it below.

Practice All PMLE Questions

Access 65 questions with complete answers and detailed explanations.

View Full PMLE Practice Test →

← Back to PMLE Study Guide