Google Professional Data Engineer
Get started today
Ultimate access to all questions.
NO.11 You work for a large real estate firm and are preparing 6 TB of home sales data to be used for machine learning. You will use SQL to transform the data and use BigQuery ML to create a machine learning model. You plan to use the model for predictions against a raw dataset that has not been transformed. How should you set up your workflow in order to prevent skew at prediction time?
Real Exam
Community
LLeetQuiz
Explanation:
Explanation:
Option A is the correct answer because:
- TRANSFORM clause in BigQuery ML automatically applies the same preprocessing during training and prediction
- Prevents data skew by ensuring consistent transformations across training and inference
- Simplified workflow - no need for separate transformation steps at prediction time
- Native BigQuery ML feature designed specifically for this use case
Reference: https://cloud.google.com/bigquery-ml/docs/bigqueryml-transform
Using the TRANSFORM clause, you can specify all preprocessing during model creation. The preprocessing is automatically applied during the prediction and evaluation phases of machine learning.
Other options would require manual transformation steps that could introduce inconsistencies and data skew.
Comments
Loading comments...