nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #116

You work for a gaming company that develops massively multiplayer online (MMO) games. You built a TensorFlow model that predicts whether players will make in-app purchases of more than $10 in the next

The correct answer is A. Import the model into BigQuery ML. Make predictions using batch reading data from BigQuery,. The prediction task is forecasting in-app purchases over the next two weeks - a future-looking batch prediction, not a real-time inference requirement. User data is already in BigQuery, so importing the trained TensorFlow model into BigQuery ML and running batch predictions direc

Submitted by tunde_lagos· Apr 18, 2026ML pipeline operationalization

Question

You work for a gaming company that develops massively multiplayer online (MMO) games. You built a TensorFlow model that predicts whether players will make in-app purchases of more than $10 in the next two weeks. The model's predictions will be used to adapt each user's game experience. User data is stored in BigQuery. How should you serve your model while optimizing cost, user experience, and ease of management?

Options

  • AImport the model into BigQuery ML. Make predictions using batch reading data from BigQuery,
  • BDeploy the model to Vertex AI Prediction. Make predictions using batch reading data from Cloud
  • CEmbed the model in the mobile application. Make predictions after every in-app purchase event is
  • DEmbed the model in the streaming Dataflow pipeline. Make predictions after every in-app

How the community answered

(22 responses)
  • A
    77% (17)
  • B
    14% (3)
  • C
    5% (1)
  • D
    5% (1)

Explanation

The prediction task is forecasting in-app purchases over the next two weeks - a future-looking batch prediction, not a real-time inference requirement. User data is already in BigQuery, so importing the trained TensorFlow model into BigQuery ML and running batch predictions directly against the BigQuery table is the most cost-effective, operationally simple solution with no separate serving infrastructure to manage. Deploying to a Vertex AI endpoint (B) introduces an online serving infrastructure that is unnecessary for batch predictions. Embedding the model in the mobile app (C) is complex to update and risky. A Dataflow streaming pipeline (D) adds unnecessary real-time infrastructure for what is a batch workload.

Topics

#Model serving#BigQuery ML#Batch prediction#MLOps

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice