QuestionQ23

Serving and scaling models

You work for a mobile-gaming startup that develops online multiplayer games. Recently, the company has seen more players cheating in its games, resulting in lost revenue and a poor user experience. You built a binary classification model to identify whether a player cheated after a game session is completed, then send a message to downstream systems to ban a player who cheated. Your model performed well in testing, and you now need to deploy it to production. You want the serving solution to return classifications immediately after a completed game session to prevent further revenue loss. What should you do?

Explanation

Vertex AI endpoints host deployed models and support online, real-time prediction requests, making them appropriate for an immediate post-session classification that triggers a downstream ban. Batch Prediction is intended for batch inference jobs rather than low-latency per-session serving. Get online inferences from a custom trained model

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!