Google
PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #88
You need to execute a batch prediction on 100 million records in a BigQuery table with a custom TensorFlow DNN regressor model, and then store the predicted results in a BigQuery table. You want to…
The correct answer is A. Import the TensorFlow model with BigQuery ML, and run the ml.predict function. https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-inference- Predict the label, either a numerical value for regression tasks or a categorical value for classification tasks on DNN regresion.
Submitted by mateo_ar· Apr 18, 2026ML pipeline operationalization
Question
You need to execute a batch prediction on 100 million records in a BigQuery table with a custom TensorFlow DNN regressor model, and then store the predicted results in a BigQuery table. You want to minimize the effort required to build this inference pipeline. What should you do?
Options
- AImport the TensorFlow model with BigQuery ML, and run the ml.predict function.
- BUse the TensorFlow BigQuery reader to load the data, and use the BigQuery API to write the
- CCreate a Dataflow pipeline to convert the data in BigQuery to TFRecords. Run a batch inference
- DLoad the TensorFlow SavedModel in a Dataflow pipeline. Use the BigQuery I/O connector with a
How the community answered
(35 responses)- A86% (30)
- B3% (1)
- C9% (3)
- D3% (1)
Explanation
https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-inference- Predict the label, either a numerical value for regression tasks or a categorical value for classification tasks on DNN regresion.
Topics
#Batch prediction#BigQuery ML#TensorFlow model deployment#ML inference
Community Discussion
No community discussion yet for this question.