Google Exam Professional Machine Learning Engineer Topic 1 Question 96 Discussion

Actual exam question for Google's Professional Machine Learning Engineer exam

Question #: 96
Topic #: 1

[All Professional Machine Learning Engineer Questions]

You are implementing a batch inference ML pipeline in Google Cloud. The model was developed by using TensorFlow and is stored in SavedModel format in Cloud Storage. You need to apply the model to a historical dataset that is stored in a BigQuery table. You want to perform inference with minimal effort. What should you do?

AImport the TensorFlow model by using the create model statement in BigQuery ML. Apply the historical data to the TensorFlow model.

BExport the historical data to Cloud Storage in Avro format. Configure a Vertex Al batch prediction job to generate predictions for the exported data.

CExport the historical data to Cloud Storage in CSV format. Configure a Vertex Al batch prediction job to generate predictions for the exported data.

DConfigure and deploy a Vertex Al endpoint. Use the endpoint to get predictions from the historical data inBigQuery.

Show Suggested Answer

Suggested Answer: B

Vertex AI batch prediction is the most appropriate and efficient way to apply a pre-trained model like TensorFlow's SavedModel to a large dataset, especially for batch processing.

The Vertex AI batch prediction job works by exporting your dataset (in this case, historical data from BigQuery) to a suitable format (like Avro or CSV) and then processing it in Cloud Storage where the model is stored.

Avro format is recommended for large datasets as it is highly efficient for data storage and is optimized for read/write operations in Google Cloud, which is why option B is correct.

Option A suggests using BigQuery ML for inference, but it does not support running arbitrary TensorFlow models directly within BigQuery ML. Hence, BigQuery ML is not a valid option for this particular task.

Option C (exporting to CSV) is a valid alternative but is less efficient compared to Avro in terms of performance.

by Precious at Jan 25, 2025, 09:18 AM

Limited Time Offer

25%

24 days ago

Option C is the way to go! Exporting the data to CSV and then using Vertex AI for batch prediction is a simple and straightforward solution.

upvoted 0 times

Sue

8 days ago

I agree, it's a simple and straightforward solution. No need to overcomplicate things.

upvoted 0 times

...

Gwenn

13 days ago

Option C is definitely the easiest way to go. Exporting to CSV and using Vertex AI for batch prediction is the way to go.

upvoted 0 times

...

Valentine

24 days ago

I think option D is the best choice. It seems like the most efficient way to get predictions from the historical data.

upvoted 0 times

...

Tegan

29 days ago

I'd go with Option D. Deploying a Vertex AI endpoint and using it to get predictions directly from BigQuery sounds like the easiest way to apply the model to the historical data.

upvoted 0 times

...

Amber

1 months ago

Option B seems the most efficient approach. Exporting the data to Cloud Storage and using Vertex AI for batch prediction is a great way to leverage the model without complicated integration.

upvoted 0 times

Cyril

18 days ago

I agree, using Vertex AI for batch prediction will make it easier to apply the model to the historical dataset.

upvoted 0 times

...

Corinne

20 days ago

I think option B is the way to go. Exporting the data to Cloud Storage and using Vertex AI for batch prediction seems efficient.

upvoted 0 times

...