Google Cloud Associate Data Practitioner — Question 57

You used BigQuery ML to build a customer purchase propensity model six months ago. You want to compare the current serving data with the historical serving data to determine whether you need to retrain the model. What should you do?

Answer options

• A. Compare the two different models.
• B. Evaluate the data skewness.
• C. Evaluate data drift.
• D. Compare the confusion matrix.

Correct answer: C

Explanation

Evaluating data drift is crucial because it helps you understand if the characteristics of the current serving data have changed significantly compared to the historical data, which may impact model performance. In contrast, comparing models, evaluating skewness, or analyzing the confusion matrix does not directly address the potential shifts in data that could necessitate retraining.