mediumMultiple Choice
PMLE Practice Question: A financial services company uses BigQuery ML to…
A financial services company uses BigQuery ML to build a logistic regression model for fraud detection. The model is trained on the last 6 months of transaction data (about 50 million rows). After deployment, the fraud detection team notices a high false positive rate, causing customer dissatisfaction and extra manual review costs. The model is currently retrained monthly. The team wants to reduce false positives without sacrificing recall. They have access to real-time transaction streaming and can compute new features quickly. What is the most effective approach?
⚠ Common exam trap
Test-takers frequently assume a more complex model (XGBoost or AutoML) is always better for reducing false positives, but the question specifically tests the principle that feature engineering—especially temporal aggregations—is the most effective lever when the model is already appropriate and data is streaming.
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
✓
Add engineered features like rolling transaction count and velocity per user
Adding engineered features like rolling transaction count and velocity per user directly addresses the high false positive rate by providing the logistic regression model with more discriminative temporal signals. Since the team has access to real-time streaming and can compute features quickly, these features capture behavioral patterns that reduce false positives without sacrificing recall, and logistic regression can effectively leverage them with proper feature engineering.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Replace logistic regression with gradient boosted trees (XGBoost) in BigQuery ML
Why it's wrong here
Swapping the algorithm does not address the false positives, which stem from features or threshold, not model family. Gradient boosted trees suit tabular accuracy gains when the existing model underfits; here the streaming features and threshold tuning are the levers.
- ✗
Use Vertex AI AutoML Tables to train a more complex model
Why it's wrong here
AutoML Tables adds model complexity but cannot reduce false positives when the underlying features omit real-time transaction context. It suits teams lacking ML expertise who need automated model selection, not a scenario where streaming feature engineering is the actual remedy.
- ✗
Increase retraining frequency to daily
Why it's wrong here
Retraining daily refreshes the model on the same features, so the false positive rate persists because the inputs lack the signal separating legitimate from fraudulent transactions. Daily retraining suits rapidly drifting fraud patterns, not a static feature set causing misclassification.
- ✓
Add engineered features like rolling transaction count and velocity per user
Why this is correct
Rolling transaction count and velocity per user capture behavioural patterns over recent windows, giving the logistic regression model stronger discriminative signals than raw transaction fields. These features directly reduce false positives while preserving recall, and real-time streaming lets them be computed at scoring time.
Go deeper
Related to this question
About these practice questions
This PMLE question is part of Courseiva's 775-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 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.