easyMultiple Choice
PMLE Practice Question: A financial company is building a fraud detection…
A financial company is building a fraud detection model. The dataset has 1% fraud cases and 99% legitimate transactions. Which technique should they use to handle the class imbalance?
⚠ Common exam trap
PMLE often tests whether candidates recognize that accuracy is not a valid metric for imbalanced data and that techniques like SMOTE or class weighting are necessary—undersampling is a common distractor but can discard critical information.
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
✓
Use class weighting or synthetic oversampling (SMOTE) during training
For highly imbalanced datasets like fraud detection (1% fraud), class weighting or synthetic oversampling (SMOTE) during training helps the model learn the minority class patterns without discarding valuable majority-class data. Class weighting adjusts the loss function to penalize minority-class misclassifications more heavily, while SMOTE generates synthetic minority samples to balance the class distribution, improving recall and F1 for the fraud class.
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 class weighting or synthetic oversampling (SMOTE) during training
Why this is correct
With only 1% fraud, a model optimising raw accuracy predicts legitimate for everything. Class weighting penalises minority-class errors more heavily, while SMOTE synthesises new minority samples, both shifting the decision boundary so fraud patterns are actually learned during training.
- ✗
Randomly undersample the majority class to balance the dataset
Why it's wrong here
Undersampling discards 99% of legitimate transactions, destroying the signal needed to recognise normal behaviour and biasing the model. It is tempting because it balances classes cheaply, and it works when the majority class is genuinely redundant, but here it removes most fraud-detection context.
- ✗
Collect more data until the fraud rate increases
Why it's wrong here
Collecting more data does not change the underlying 1% fraud prevalence; the ratio stays skewed unless sampling is applied. Gathering more fraud examples is worthwhile when absolute fraud volume is too small to learn from, but it addresses data quantity, not class imbalance itself.
- ✗
Train without any modifications; the model will naturally handle it
Why it's wrong here
Training unmodified on a 1% positive rate lets the model minimise loss by predicting legitimate for everything, yielding high accuracy but near-zero fraud recall. This is tempting because some algorithms tolerate mild skew, yet severe imbalance requires weighting, resampling or threshold tuning.
Go deeper
Related to this question
About these practice questions
One of 775 original PMLE 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 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.