AIF-C01 Fundamentals of AI and ML Practice Question
A team trained a deep learning model that achieves 99% accuracy on training data but only 70% on validation data. What is the most likely issue?
⚠ Common exam trap
The AIF-C01 exam often tests the distinction between overfitting and underfitting by presenting a scenario where training accuracy is high but validation accuracy is low, tempting candidates to incorrectly choose underfitting if they focus only on the low validation score.
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
✓
Overfitting
The model performs exceptionally well on training data (99% accuracy) but significantly worse on validation data (70% accuracy). This large gap indicates the model has memorized the training data, including noise and irrelevant patterns, rather than learning generalizable features — a classic symptom of overfitting.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Underfitting
Why it's wrong here
Underfitting means poor performance on both training and validation data, whereas here training accuracy is 99%. It is tempting because the 70% validation figure looks like insufficient learning, and it would be correct if both scores were low, but the large train-validation gap indicates variance, not bias.
- ✓
Overfitting
Why this is correct
The large gap between 99% training accuracy and 70% validation accuracy shows the model memorised training data rather than learning generalisable patterns. Overfitting is the specific condition producing this divergence, matching the stem's reported metrics exactly.
- ✗
Data leakage
Why it's wrong here
Data leakage inflates validation performance because training information contaminates the validation set, producing a high validation score. Here validation is far lower than training, the opposite pattern. It is tempting because leakage is a common pitfall, and it would be correct if validation accuracy unexpectedly exceeded training accuracy.
- ✗
Feature scaling
Why it's wrong here
Feature scaling affects convergence speed and numerical stability, not the train-validation gap; unscaled features typically slow training rather than cause a 29-point generalisation gap. It is tempting because scaling is a standard preprocessing step, and it would be correct for fixing slow or unstable gradient descent, not overfitting.
Go deeper
Related to this question
About these practice questions
This AIF-C01 question is part of Courseiva's 862-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services 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 AIF-C01 exam.