mediumMultiple Choice
PDE Practice Question: A company uses BigQuery ML to create a…
A company uses BigQuery ML to create a classification model. The model is used for batch prediction on a weekly basis. After six months, the data distribution shifts, and model accuracy drops. Which approach should the company take to maintain model performance?
⚠ Common exam trap
Google Cloud often tests the misconception that hyperparameter tuning or feature engineering alone can fix data drift, when in fact only retraining on fresh data addresses the shift.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Schedule automatic retraining of the model using the most recent three months of data.
The model's accuracy drop is due to data distribution shift (concept drift). Scheduling automatic retraining using the most recent three months of data ensures the model adapts to the new patterns without manual intervention. BigQuery ML supports scheduled queries and automatic model retraining via the `CREATE OR REPLACE MODEL` statement, making this approach both practical and aligned with MLOps best practices for batch prediction pipelines.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use Cloud Dataflow to preprocess the data and then update the model with new features.
Why it's wrong here
Dataflow preprocessing with new features addresses feature engineering, not the distribution shift that degraded the model; retraining on recent data is required. It is tempting because Dataflow is the standard tool for large-scale preprocessing pipelines feeding BigQuery ML, and feature updates do help when the problem is missing signal.
- ✗
Perform hyperparameter tuning on the original training data.
Why it's wrong here
Hyperparameter tuning searches configurations against the original training data, which no longer reflects the shifted distribution, so accuracy stays degraded. It is tempting because tuning is a standard accuracy-improvement step, and it would be correct if the model were underfit rather than affected by drift.
- ✗
Apply model quantization to reduce model size and improve inference speed.
Why it's wrong here
Quantization shrinks weights and speeds inference; it does not restore accuracy lost to data drift and can reduce it further. It is tempting because it is a legitimate optimisation for latency- or cost-constrained serving, and improved inference speed can superficially look like improved model performance.
- ✓
Schedule automatic retraining of the model using the most recent three months of data.
Why this is correct
Scheduled retraining on the most recent three months of data refreshes the model against current distributions, countering the drift that degraded accuracy. This satisfies the requirement to maintain performance after six months of distribution shift, without manual intervention each cycle.
Go deeper
Related to this question
About these practice questions
This PDE question is part of Courseiva's 747-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This PDE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PDE exam.