PDE Practice Question: Responsible for monitoring a production ML model…

You are responsible for monitoring a production ML model on Vertex AI. The model predicts loan approval probability. The business team reports that the model's predictions are becoming less accurate over the last week. You check the model's monitoring dashboard and see that the prediction distribution has changed significantly. What is the most likely issue?

⚠ Common exam trap

Google Cloud often tests the distinction between data drift and concept drift, and the trap here is that candidates see 'prediction distribution has changed' and incorrectly assume it must be data drift, when in fact a change in prediction distribution without a change in input features is a classic sign of concept drift.

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

✓

The model is experiencing concept drift.

Concept drift occurs when the underlying relationship between input features and the target variable changes over time, causing the model's predictions to become less accurate even if the input data distribution remains stable. In this scenario, the prediction distribution has changed significantly, which is a hallmark of concept drift, as the model's learned decision boundary no longer reflects the current real-world patterns. Vertex AI's monitoring dashboard can track prediction distribution shifts, and this symptom points to concept drift rather than data drift.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
The model is suffering from overfitting to the training data.
Why it's wrong here
Overfitting would cause poor generalization from the start, not a gradual decline after deployment.
✗
There is a bug in the model's preprocessing code.
Why it's wrong here
A code bug would cause consistent errors, not gradual accuracy decline.
✗
There is data drift in the input features.
Why it's wrong here
Data drift would change input distribution, but the question says prediction distribution changed; it could be concept drift.
✓
The model is experiencing concept drift.
Why this is correct
Concept drift means the underlying relationship between features and target has changed, causing prediction distribution to shift and accuracy to drop.

Go deeper

PDE Practice Question: Responsible for monitoring a production ML model…

Why each option matters

Option-by-option breakdown

Related to this question