AI-900 Practice Question: Describe fundamental principles of machine learning on Azure
A data scientist trains a regression model to predict house prices. The model performs poorly on both the training data and the test data, showing high error in both sets. Which concept best describes this situation?
⚠ Common exam trap
It's easy for candidates to confuse underfitting with overfitting because both involve poor performance, but the key distinction is that underfitting shows high error on both training and test sets, while overfitting shows low training error and high test error.
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
✓
Underfitting
Underfitting occurs when a model is too simple to capture the underlying patterns in the data, resulting in high error on both the training and test sets. In this regression scenario, the model fails to learn the relationship between features and house prices, leading to poor performance across all data splits.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Overfitting
Why it's wrong here
Overfitting is characterized by a model that memorizes training data, including its noise, so training loss is typically very low while test loss is high. This creates a wide performance gap, not uniformly high error on both splits. Since the scenario describes high error on training and test sets alike, overfitting cannot explain the pattern; the model would at least succeed on the data it was fitted to.
- ✓
Underfitting
Why this is correct
Underfitting occurs when the model is too simplistic to capture the underlying relationship in the data, such as using a linear regression for a strongly nonlinear relationship or omitting key features. This high-bias state causes the model to make large, systematic errors on both the training set and the test set. The symptom of poor performance on all data splits is the hallmark of underfitting, matching the scenario described.
- ✗
Data leakage
Why it's wrong here
Data leakage happens when information from the target variable or from the test set is unintentionally used during training, such as through target-encoded features or improper preprocessing applied before splitting. Leakage typically inflates model evaluation metrics and makes test performance look unrealistically good, not poor. Therefore, it would produce the opposite symptom—abnormally high accuracy—rather than high error on both training and test data.
- ✗
Feature scaling
Why it's wrong here
Feature scaling, such as standardization or normalization, is a preprocessing technique that improves optimization convergence and ensures equal influence of feature magnitudes, especially for gradient-based models or distance-based algorithms. Omitting feature scaling can slow training or cause poor convergence in extreme cases, but it does not inherently cause high error across both training and test sets. The model can still learn the pattern with enough iterations, so scaling is not a fundamental cause of underfitting.
Go deeper
Related to this question
Learn chapter
Regression and Classification
Key term
Model
In IT and AI, a model is a trained mathematical representation that learns patterns from data to make predictions or decisions.
Key term
Underfitting
Underfitting occurs when a machine learning model is too simple to capture the underlying patterns in the training data, resulting in poor performance on both training and new data.
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 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-900 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-900 exam.