AI0-001 AI Governance and Ethics Practice Question
A data scientist needs to explain why a black-box model denied a loan application. Which explainability technique generates local feature importance values using a simpler interpretable model around the prediction?
⚠ Common exam trap
The AI0-001 exam often tests the distinction between local vs. global explainability methods, and the trap here is that candidates may confuse SHAP values (which also provide local feature importance) with LIME, failing to recognize that LIME uniquely uses a simpler interpretable surrogate model trained around the prediction, while SHAP uses game-theoretic contributions without a surrogate model.
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
✓
LIME
LIME (Local Interpretable Model-agnostic Explanations) is the correct technique because it generates local feature importance values by fitting a simpler, interpretable model (e.g., linear regression or decision tree) around the prediction of the black-box model. This allows the data scientist to explain why a specific loan application was denied by identifying which features (e.g., income, credit score) most influenced that particular decision. Unlike global methods, LIME focuses on the local neighborhood of the instance, making it ideal for explaining individual predictions.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Model card
Why it's wrong here
A model card is static documentation describing a model's intended use, performance and limitations; it computes no local feature importance for an individual prediction. It is tempting because model cards support transparency and accountability, and would be correct when the data scientist must document a model's overall characteristics for governance.
- ✓
LIME
Why this is correct
LIME fits a simple interpretable surrogate model, such as a linear model, around the individual prediction and reports local feature importance for that single loan decision. This satisfies the stem's demand for local explanation of a black-box model's specific output.
- ✗
Attention visualisation
Why it's wrong here
Attention visualisation exposes which input tokens a transformer weighted, giving no local feature-importance values for tabular loan features. It is tempting because it explains individual predictions in NLP models. LIME builds a locally weighted interpretable surrogate around the prediction, which is what the scenario requires.
- ✗
SHAP values
Why it's wrong here
SHAP values compute Shapley-based additive feature attributions across the whole coalition space, not a surrogate model fitted locally around one prediction. It is tempting because SHAP also delivers local, per-prediction importance and is model-agnostic, but LIME is the technique that trains a sparse interpretable surrogate on perturbed samples near the instance.
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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.