AI0-001 Implementing AI Solutions Practice Question
A company is building an AI-powered document intelligence system to extract key fields from scanned invoices. The data contains 95% of invoices from one vendor and 5% from others. During model training, the F1 score is 0.95 on the overall test set, but the performance on the minority vendor invoices is very poor. What is the MOST likely cause?
⚠ Common exam trap
AI0-001 often tests the misconception that a high overall F1 score guarantees good performance across all classes, but candidates must recognize that imbalanced datasets can mask poor minority class performance.
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 dataset is imbalanced, and the model is biased toward the majority class
The F1 score of 0.95 on the overall test set is misleading because 95% of invoices come from one vendor, so the model can achieve high overall accuracy by performing well on the majority class while failing on the minority class. This is a classic class imbalance problem where the model is biased toward the majority class. The poor performance on minority vendor invoices confirms that the model has not learned to generalize across vendors.
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 overfitting on the minority class
Why it's wrong here
Overfitting affects all classes and shows as poor generalisation on the test set, yet overall F1 is 0.95. The model fits the majority vendor well and the minority poorly, which is imbalance, not overfitting. Overfitting would be the answer if training accuracy far exceeded test accuracy.
- ✓
The dataset is imbalanced, and the model is biased toward the majority class
Why this is correct
With 95% of invoices from one vendor, the model optimises for the majority class, so minority-vendor patterns are underweighted during training. High overall F1 masks this, since majority-class performance dominates the metric. The poor minority-vendor results stem directly from this class imbalance, not from overfitting or feature scaling.
- ✗
The data has a train/test leakage problem
Why it's wrong here
Leakage would inflate scores across all vendors, not selectively depress the 5% minority. The 95/5 split points to class imbalance skewing the model toward the majority vendor. Leakage is worth suspecting when test metrics look implausibly high overall, but here the minority failure is the signal.
- ✗
The feature extraction is incorrect for the minority vendor invoices
Why it's wrong here
Feature extraction runs identically across vendors; nothing in the stem suggests vendor-specific parsing failures. The imbalance itself, not the extraction pipeline, explains why minority invoices are misclassified. Incorrect extraction would be the cause if minority invoices used a distinct layout the parser could not handle.
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.