AI0-001 AI Concepts and Techniques Practice Question
A financial services firm is designing an AI system to detect fraudulent transactions. The dataset is highly imbalanced, with fraud representing less than 0.1% of transactions. The team wants to build a model that reliably identifies fraud while minimizing false positives that inconvenience customers. Which TWO techniques are MOST appropriate to address the class imbalance and evaluation needs? (Choose two.)
⚠ Common exam trap
The trap here is prioritizing overall accuracy in an imbalanced fraud scenario, which rewards majority-class predictions and hides the model's failure to detect fraud.
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
✓
Apply class weighting or resampling to give more importance to fraudulent transactions
The two appropriate techniques are using precision-recall AUC for evaluation and applying class weighting or resampling. Precision-recall AUC highlights performance on the rare fraud class, while class weighting or resampling ensures the model learns from fraud examples. Together they address both the training imbalance and the need for meaningful evaluation, supporting reliable fraud detection with controlled false positives.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the number of layers in the neural network to improve capacity
Why it's wrong here
Adding layers increases model complexity but does not address the class imbalance. The model may still ignore the minority class because the loss is dominated by non-fraud examples. Without rebalancing or appropriate metrics, deeper networks can overfit the majority class and fail to improve fraud detection, so this is not an appropriate primary remedy.
- ✓
Apply class weighting or resampling to give more importance to fraudulent transactions
Why this is correct
Class weighting or resampling adjusts the training process so that the rare fraud class has more influence. This helps the model learn fraud patterns instead of defaulting to the majority class. Combined with appropriate evaluation, this technique directly addresses the imbalance and supports reliable fraud detection while allowing control over false positives through threshold tuning.
- ✗
Remove all non-fraud transactions to balance the dataset
Why it's wrong here
Removing all non-fraud transactions would discard the vast majority of data and eliminate the ability to learn the normal transaction distribution. This would likely cause many false positives and poor generalization. Proper resampling techniques balance classes without discarding all majority examples, and evaluation must still reflect realistic class proportions.
- ✗
Optimize only for accuracy to ensure overall correctness
Why it's wrong here
Optimizing for accuracy on an imbalanced dataset encourages the model to predict the majority class, achieving high accuracy while missing nearly all fraud. This directly conflicts with the goal of reliably identifying fraud. Accuracy is an inappropriate metric here, and relying on it would lead to a model that fails in production despite impressive-looking scores.
- ✓
Use precision-recall AUC instead of accuracy to evaluate model performance
Why this is correct
Precision-recall AUC is well suited for highly imbalanced datasets because it focuses on the minority class and reflects the trade-off between precision and recall. Accuracy would be misleadingly high due to the dominance of non-fraud transactions. Using precision-recall AUC helps the team select a model that detects fraud without excessive false positives, directly supporting their goal.
About these practice questions
One of 962 original AI0-001 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 CompTIA exam blueprint
This AI0-001 practice question is part of Courseiva's free CompTIA 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 AI0-001 exam.