You Have a Demand Forecasting Pipeline in Production That Uses

question 7

Multiple Choice

You have a demand forecasting pipeline in production that uses Dataflow to preprocess raw data prior to model training and prediction. During preprocessing, you employ Z-score normalization on data stored in BigQuery and write it back to BigQuery. New training data is added every week. You want to make the process more efficient by minimizing computation time and manual intervention. What should you do?

• A) Normalize the data using Google Kubernetes Engine.
• B) Translate the normalization algorithm into SQL for use with BigQuery.
• C) Use the normalizer_fn argument in TensorFlow's Feature Column API. Use the normalizer_fn argument in TensorFlow's Feature Column API.
• D) Normalize the data with Apache Spark using the Dataproc connector for BigQuery.

---

Definitions:

Gratuitous

Provided without requiring anything in return; given freely or without charge.

Service

The provision of assistance or professional work performed for another person or organization.

Quantum Meruit

A legal principle meaning "as much as he has deserved," used to determine the amount of compensation due for services provided when there is no existing contract.

Service

The action or process of serving or providing assistance to others, often in the context of customers or clients.