Google Cloud Professional Machine Learning Engineer — Question 338

You have trained a model on a dataset that required computationally expensive preprocessing operations. You need to execute the same preprocessing at prediction time. You deployed the model on AI Platform for high-throughput online prediction. Which architecture should you use?

Answer options

• A. Validate the accuracy of the model that you trained on preprocessed data. Create a new model that uses the raw data and is available in real time. Deploy the new model onto AI Platform for online prediction.
• B. Send incoming prediction requests to a Pub/Sub topic. Transform the incoming data using a Dataflow job. Submit a prediction request to AI Platform using the transformed data. Write the predictions to an outbound Pub/Sub queue.
• C. Stream incoming prediction request data into Cloud Spanner. Create a view to abstract your preprocessing logic. Query the view every second for new records. Submit a prediction request to AI Platform using the transformed data. Write the predictions to an outbound Pub/Sub queue.
• D. Send incoming prediction requests to a Pub/Sub topic. Set up a Cloud Function that is triggered when messages are published to the Pub/Sub topic. Implement your preprocessing logic in the Cloud Function. Submit a prediction request to AI Platform using the transformed data. Write the predictions to an outbound Pub/Sub queue.

Correct answer: B

Explanation

Option B is correct because it efficiently utilizes a Dataflow job to transform incoming data in real-time before submitting it to AI Platform for predictions, ensuring that the preprocessing is handled seamlessly. Options A and C suggest creating new architectures that do not address the need for real-time preprocessing at scale. Option D, while it uses a Pub/Sub topic, may not handle high-throughput as effectively as a Dataflow job does.