AI0-001 AI Models and Data Engineering Practice Question
A machine learning engineer is training a Support Vector Machine (SVM) with an RBF kernel on a dataset with features on different scales (e.g., age 0-100, income 0-1,000,000). The model converges slowly and yields poor accuracy. What should the engineer do first?
⚠ Common exam trap
The CompTIA AI+ exam often tests the misconception that hyperparameter tuning (C or gamma) is the primary fix for poor SVM performance, when in reality feature scaling is a prerequisite for distance-based kernels like RBF.
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
✓
Standardize the features to have zero mean and unit variance
Standardizing features to zero mean and unit variance is the correct first step because SVMs with RBF kernels are distance-based models. Features on vastly different scales (e.g., age 0-100 vs. income 0-1,000,000) cause the kernel to disproportionately weight larger-scale features, leading to slow convergence and poor accuracy. Standardization ensures each feature contributes equally to the distance calculations, improving both training speed and model performance.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Standardize the features to have zero mean and unit variance
Why this is correct
The RBF kernel relies on Euclidean distance, so unscaled features such as income dominate age, distorting the kernel and slowing convergence. Standardising to zero mean and unit variance equalises feature influence, directly addressing the scale disparity.
- ✗
Increase the regularization parameter C to penalize misclassifications more
Why it's wrong here
C controls the trade-off between margin and error, not the scale sensitivity.
- ✗
Decrease the gamma parameter to reduce the influence of each data point
Why it's wrong here
Gamma controls the radius of influence of a single training example, not the relative weighting of unscaled features; lowering it widens each point's reach but income still dwarfs age in the distance calculation. It is tempting because gamma tuning is a standard RBF remedy, and would be correct once features are scaled.
- ✗
Switch to a linear kernel to avoid distance calculations
Why it's wrong here
A linear kernel still computes dot products on the raw features, so the income column's far larger magnitude continues to dominate the decision boundary and convergence. It is tempting because linear kernels avoid the RBF kernel's distance computations, and would suit linearly separable data, but the stem's problem is feature scaling.
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 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.