mediumMultiple Choice
PDE Practice Question: Your team has implemented a CI/CD pipeline using…
Your team has implemented a CI/CD pipeline using Cloud Composer (Apache Airflow) to retrain a model every day. The pipeline reads new data from BigQuery, trains a model using Vertex AI Training, evaluates it, and if the accuracy improves, deploys it to a Vertex AI Endpoint. For the past week, the pipeline has been running successfully but no new model has been deployed because the evaluation accuracy never exceeds the previous model's accuracy. The training data volume has been consistent. You suspect that the model is not learning from the new data. What should you do?
⚠ Common exam trap
PDE often tests the misconception that more training or a different metric will fix a model that is not learning, when the real issue is usually data quality or feature engineering.
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
✓
Examine the training data for any data quality issues such as missing values or label leakage.
When a model trained on consistent data volume fails to improve accuracy over a week, the most likely root cause is a data quality problem rather than a training capacity problem. Missing values, label leakage, or corrupted features can prevent the model from learning meaningful patterns, causing accuracy to plateau or degrade. Examining the training data for these issues is the correct diagnostic step before changing hyperparameters or deployment strategy.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Deploy the new model anyway and run an A/B test in production to see if it performs better online.
Why it's wrong here
Deploying an unvalidated model bypasses the accuracy gate that protects production, and an A/B test cannot fix training that ignores new data. It appeals because A/B testing is the standard way to compare candidate models against live traffic once offline evaluation has already shown a genuine improvement.
- ✓
Examine the training data for any data quality issues such as missing values or label leakage.
Why this is correct
Consistent data volume with no accuracy improvement points to data quality problems such as missing values or label leakage, which prevent the model learning new patterns. Inspecting the training data directly identifies whether inputs are corrupted before tuning hyperparameters.
- ✗
Increase the training budget or number of training steps to allow the model to converge better.
Why it's wrong here
More steps or budget cannot help if the training job never reads the new BigQuery data; convergence is not the bottleneck. It tempts because underfitting genuinely does respond to longer training, so this is the right fix when a model is converging prematurely on a correctly wired dataset.
- ✗
Change the evaluation metric to a different one that may show improvement, such as F1 score instead of accuracy.
Why it's wrong here
Swapping to F1 merely changes the yardstick; the model still fails to learn from new data, so the underlying defect persists. It tempts because F1 is the correct metric when class imbalance makes accuracy misleading, which is a legitimate scenario distinct from this one.
Go deeper
Related to this question
About these practice questions
One of 747 original PDE practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Google Cloud exam blueprint
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.