How to deploy a model for immediate real-time inference?

You work at a mobile gaming startup that creates online multiplayer games. Recently, your company observed an increase in players cheating in the games, leading to a loss of revenue and a poor user experience You built a binary classification model to determine whether a player cheated after a completed game session, and then send a message to other downstream systems to ban the player that cheated. Your model has performed well during testing, and you now need to deploy the model to production. You want your serving solution to provide immediate classifications after a completed game session to avoid further loss of revenue. What should you do?

Import the model into Vertex AI Model Registry. Use the Vertex Batch Prediction service to run batch inference jobs.
Save the model files in a Cloud Storage bucket. Create a Cloud Function to read the model files and make online inference requests on the Cloud Function.
Save the model files in a VM. Load the model files each time there is a prediction request, and run an inference job on the VM
Import the model into Vertex AI Model Registry. Create a Vertex AI endpoint that hosts the model, and make online inference requests. Source Reference Answer

Community Votes

100%

100% of anonymous learners picked answer D. Votes are pick records left by other test-takers — they are not the verified answer.

Community Insight

This question tests your ability to select the correct serving infrastructure based on latency requirements, distinguishing between online prediction for real-time needs and batch prediction for offline processing.

To prevent revenue loss from cheaters, the model must provide immediate classifications, requiring a low-latency serving solution. The community consensus is that Vertex AI Endpoints are the optimal choice for real-time inference compared to batch processing or unmanaged infrastructure.

Selecting Vertex Batch Prediction (Option A) is a common error because, while it is a powerful tool for processing large datasets, it does not support the immediate, real-time response times required for this gaming scenario.

Community Discussion (3 comments)

guilhermebutzke 👍 6

My answer: D A: Not correct: Batch Prediction is designed for offline processing of large datasets, not for immediate real-time predictions needed in this scenario. B: Not correct: While Cloud Functions offer real-time processing, loading the model files each time might introduce latency, especially for larger models C: Not correct: Using a VM is less scalable and more complex to manage compared to other options. D: CORRECT: Vertex AI Model Registry ensures proper model management, versioning, and access control while Vertex AI endpoint provides a highly scalable and managed solution for real-time online inference, ensuring immediate predictions after game sessions.

fitri001 👍 5 Selected: D

Low Latency: Vertex AI Endpoints are specifically designed for low-latency online inference. They offer automatic scaling and efficient resource allocation, ensuring quick responses to game session completion signals. Real-time Decisions: This deployment method allows your game backend to send data from finished game sessions to the Vertex AI endpoint in near real-time. The endpoint can then make classifications (cheater or not cheater) promptly. Managed Service: Vertex AI handles the infrastructure management and scaling of your model, freeing you from managing servers or virtual machines (VMs).

pikachu007 👍 3 Selected: D

Option A: Batch prediction is too slow for your needs. Option B: Cloud Functions are ideal for short-lived tasks, not for continuously serving models. Loading the model on every request would be inefficient. Option C: VMs offer less scalability and management overhead compared to Vertex AI.

Comments & Corrections

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

Expert Analysis

Why the Answer Is Correct

Vertex AI Endpoints are specifically designed for online inference, providing low-latency predictions by keeping the model loaded in memory and handling scaling automatically. This architecture allows the system to immediately classify a game session and trigger a ban, minimizing revenue loss.

Why the Other Options Are Wrong

Option A is incorrect because Batch Prediction is intended for offline, high-throughput processing of large data volumes, not real-time responses. Option B is inefficient because loading model files into a Cloud Function on every request introduces significant latency. Option C involves unnecessary operational overhead and poor performance design by reloading the model for each request on a VM.

Community Comment Notes

Community members consistently highlighted the keyword "immediate" as the deciding factor, ruling out batch processing. They also noted the inefficiency of Options B and C regarding model loading, emphasizing that Vertex AI Endpoints offer the necessary automatic scaling and resource allocation for low latency.

Official Reference

https://cloud.google.com/vertex-ai/docs/predictions/online-prediction

Exam Strategy

Identify keywords like "immediate," "real-time," or "low latency" to immediately eliminate Batch Prediction options. Be wary of solutions that suggest loading model files per request, as this creates performance bottlenecks compared to managed serving endpoints.

Related Analysis

Practice All PMLE Questions

Access 65 questions with complete answers and detailed explanations.

View Full PMLE Practice Test →

← Back to PMLE Study Guide