AI-102 Plan and manage an Azure AI solution Practice Question
You deploy a custom vision model using Azure AI Custom Vision. After deployment, you notice the model has high accuracy on training data but low accuracy on new images. What is the most likely cause?
⚠ Common exam trap
Watch out — candidates often confuse 'too few images' (a contributing factor) with the direct diagnosis of 'overfitting,' but the question asks for the most likely cause of the described symptom, which is the overfitting itself, not its root cause.
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 model is overfitted to the training data
High accuracy on training data but low accuracy on new images is the classic symptom of overfitting, where the model has memorized the training examples (including noise and irrelevant patterns) rather than learning generalizable features. In Azure AI Custom Vision, this typically occurs when the training dataset is too small, too homogeneous, or lacks sufficient variation, causing the model to fail on unseen 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.
- ✗
The training time was too short
Why it's wrong here
Insufficient training time produces underfitting — poor accuracy on training data too — whereas high training accuracy with poor new-image accuracy indicates overfitting, typically from too few or too similar training images. Longer training would worsen overfitting; more varied data or augmentation addresses it.
- ✗
The training dataset has too few images
Why it's wrong here
Insufficient images typically cause underfitting, producing poor accuracy on both training and new data. The stem describes overfitting, where the model memorises training images and fails to generalise. Adding images is the right remedy only when a model cannot learn the training patterns at all.
- ✗
The wrong domain was selected during training
Why it's wrong here
A wrong domain shifts preprocessing and network characteristics, degrading both training and validation accuracy rather than producing the high-training, low-new-data gap described. Domain selection is tempting because it affects model architecture, but the stated symptom is overfitting, caused by limited or unrepresentative training images.
- ✓
The model is overfitted to the training data
Why this is correct
Overfitting occurs when the model memorises training images rather than learning generalisable features, producing high training accuracy but poor performance on unseen images. The gap between training and new-image accuracy is the defining symptom, so more varied training data or augmentation is needed.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 practice question is part of Courseiva's free Microsoft 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 AI-102 exam.