PMLE Architecting Low-Code ML Solutions Practice Question
A marketing team wants to build a model to predict which customers are likely to churn. They have a BigQuery table with customer demographics, usage metrics, and a binary churn label. They want to use BigQuery ML and need to evaluate the model's performance. Which two statements are true regarding model evaluation in BigQuery ML? (Choose two.)
⚠ Common exam trap
Many candidates confuse prediction with evaluation; ML.PREDICT does not evaluate, and ML.TRAINING_INFO does not provide classification metrics.
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
✓
ML.CONFUSION_MATRIX can be used to visualize the confusion matrix of a classification model.
ML.EVALUATE computes standard classification metrics, and ML.CONFUSION_MATRIX provides a detailed breakdown of prediction outcomes. Both are essential for assessing a churn model. The other functions serve different purposes: ML.PREDICT for scoring, ML.TRAINING_INFO for training details, and ML.FEATURE_INFO for feature statistics.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
ML.FEATURE_INFO returns the importance of each feature in the model.
Why it's wrong here
ML.FEATURE_INFO provides statistics about the features used in training, such as min, max, and mean, but not feature importance. For feature importance, you would use ML.EXPLAIN_PREDICT or ML.GLOBAL_EXPLAIN. Thus, it does not help in evaluating model performance.
- ✗
ML.PREDICT automatically calculates the model's accuracy on the input data.
Why it's wrong here
ML.PREDICT is used to generate predictions on new data. It does not compute evaluation metrics like accuracy; it only outputs predicted labels and probabilities. To evaluate performance, you must use ML.EVALUATE on a labeled dataset. Relying on ML.PREDICT for evaluation would be incorrect.
- ✗
ML.TRAINING_INFO provides the evaluation metrics for the trained model.
Why it's wrong here
ML.TRAINING_INFO returns information about the training runs, such as iteration number, loss, and duration. It does not provide evaluation metrics like precision or recall. Those are obtained via ML.EVALUATE. Using ML.TRAINING_INFO for performance assessment would not give the needed classification metrics.
- ✓
ML.CONFUSION_MATRIX can be used to visualize the confusion matrix of a classification model.
Why this is correct
ML.CONFUSION_MATRIX generates a confusion matrix showing true positives, true negatives, false positives, and false negatives. This is useful for understanding the types of errors the model makes, which is critical when the cost of false positives and false negatives differs, as in churn prediction.
- ✓
ML.EVALUATE returns metrics such as precision, recall, accuracy, and AUC for classification models.
Why this is correct
ML.EVALUATE is the standard function to assess model performance. For classification models, it returns a range of metrics including precision, recall, accuracy, F1 score, log loss, and AUC. This allows the team to understand how well the model distinguishes churners from non-churners and to compare different models.
Go deeper
Related to this question
About these practice questions
Courseiva writes every PMLE question from scratch — 775 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. 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 PMLE 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 PMLE exam.