AI0-001 AI Concepts and Techniques Practice Question
A data scientist is evaluating a binary classification model. The model achieves 95% accuracy on the test set, but the precision is 0.60 and recall is 0.55. The dataset has 90% negative class samples. Which metric should the team focus on to improve the model?
⚠ Common exam trap
AI0-001 often tests metric selection on imbalanced data, so candidates pick accuracy because it looks high, missing that it is the wrong optimisation target when the positive class is rare.
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
✓
F1 score
With 90% negative class samples, accuracy is misleading because a trivial majority-class classifier would score 90%. The low precision (0.60) and recall (0.55) indicate the model struggles on the minority positive class. The F1 score, being the harmonic mean of precision and recall, is the right metric to optimise because it balances both concerns on imbalanced data.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
F1 score
Why this is correct
With 90% negatives, accuracy is misleading because predicting the majority class alone scores 0.90. F1 is the harmonic mean of precision and recall, so optimising it directly penalises both false positives and false negatives, addressing the weak 0.60/0.55 balance.
- ✗
Perplexity
Why it's wrong here
Perplexity measures how well a language model predicts token sequences, so it cannot evaluate a binary classifier's precision or recall on imbalanced data. It is tempting because it is a genuine model-evaluation metric, and would be correct when assessing a generative language model rather than a classifier.
- ✗
BLEU score
Why it's wrong here
BLEU compares generated text against reference translations, so it cannot measure precision or recall of a binary classifier. It is tempting because it is a recognised evaluation metric, and would be correct when scoring machine-translation or text-generation output rather than classification performance.
- ✗
Accuracy
Why it's wrong here
Accuracy is already 95% yet misleading here: with 90% negatives, predicting the majority class alone yields 90%, so accuracy hides poor minority-class performance. It is tempting because it is the headline metric, and would be correct on a balanced dataset where classes are equally represented.
About these practice questions
Courseiva writes every AI0-001 question from scratch — 962 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 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.