AI0-001 Machine Learning and Deep Learning Practice Question
A data scientist is training a random forest model on a large dataset and notices that the model is overfitting. Which hyperparameter adjustment is most likely to reduce overfitting?
⚠ Common exam trap
A common mistake is assuming that increasing the number of trees always reduces overfitting, but in random forests, while more trees reduce variance through averaging, they do not address the root cause of overfitting in individual trees. Decreasing maximum depth directly limits tree complexity.
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
✓
Decrease the maximum depth of trees
Decreasing the maximum depth of trees limits how deep each decision tree can grow, which reduces the model's capacity to learn overly specific patterns from the training data. This directly combats overfitting by enforcing simpler trees that generalize better to 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.
- ✗
Increase the maximum features
Why it's wrong here
Raising maximum features lets each split consider more variables, increasing tree correlation and variance, so overfitting worsens rather than eases. It is tempting because extra features can improve training accuracy, and it would suit a model that is underfitting and needs greater flexibility to capture signal.
- ✓
Decrease the maximum depth of trees
Why this is correct
Maximum depth controls how many splits each tree can make. Reducing it constrains tree complexity, limiting the model's ability to memorise training noise, which lowers variance and reduces overfitting. Increasing depth or adding trees would typically worsen the overfitting observed.
- ✗
Decrease the minimum samples split
Why it's wrong here
Decreasing minimum samples split lets trees split on smaller, noisier subsets, deepening them and worsening overfitting. Raising that threshold is the regularising direction; the option would be selected when underfitting and needing finer-grained splits to capture structure.
- ✗
Increase the number of trees
Why it's wrong here
Adding trees reduces variance in the averaged prediction but does not constrain individual trees from fitting noise, so overfitting persists. More trees would be chosen when seeking stable predictions on an already well-regularised model; limiting depth or raising minimum samples per leaf addresses overfitting.
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.