k-Fold Cross-Validation: k=10 vs k=5
What is 'k-fold cross-validation' specifically and how is k=10 different from k=5?
Quick Answer
The answer is that k=10 provides more reliable performance estimates at roughly twice the computational cost of k=5. This difference stems from how k-fold cross-validation works: the dataset is split into k equal folds, with the model trained on k-1 folds and validated on the remaining fold, repeated k times. With k=10, each model trains on 90% of the data and validates on 10%, averaging results over ten runs to produce a lower-variance estimate; k=5 uses 80% training and 20% validation over only five runs, which is faster but more prone to variance in the performance metric. On the AI-900 exam, this concept tests your understanding of bias-variance trade-offs in model evaluation—a common trap is assuming more folds always improve accuracy, when in fact the gain is in reliability, not raw accuracy. A simple memory tip: “Ten folds, ten times the trust; five folds, half the cost.”
⚠ Common exam trap
It's easy for candidates to confuse model performance improvement with estimate reliability; candidates often think more folds always yield a better model, but cross-validation is about evaluating performance, not training the final model.
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
✓
k=10 provides more reliable performance estimates at 2x the compute cost vs k=5
k-fold cross-validation splits the dataset into k equal folds, training on k-1 folds and validating on the remaining fold, repeating this process k times. With k=10, each model is trained on 90% of the data and validated on 10%, while k=5 uses 80% for training and 20% for validation. The key difference is that k=10 yields a performance estimate with lower variance (more reliable) because it averages over more folds, but it requires approximately twice the computational cost (10 training runs vs. 5).
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
k=10 always produces a better model than k=5 because it uses more training data
Why it's wrong here
More folds gives better estimation reliability, not necessarily better models — the same total data is used either way.
- ✓
k=10 provides more reliable performance estimates at 2x the compute cost vs k=5
Why this is correct
More folds = less variance in the performance estimate, but more training runs — k=10 is more reliable but computationally costlier than k=5.
- ✗
k=5 and k=10 produce identical results because the total data is the same
Why it's wrong here
More folds reduce variance in the performance estimate — k=10 gives a more reliable estimate than k=5 despite using the same data.
- ✗
k=10 requires 10 times more labelled data than k=5
Why it's wrong here
Both work with the same dataset size — k determines how many times you split and train, not how much data you need.
Go deeper
Related to this question
About these practice questions
This AI-900 question is part of Courseiva's 985-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 →
Same concept, more angles
2 more ways this is tested on AI-900
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. What is 'cross-validation' and when should it be used in machine learning?
medium- A.Validating that a model works correctly across different Azure regions
- ✓ B.Dividing data into k folds and training k times to get a more reliable performance estimate
- C.Comparing two different models' predictions on the same test set
- D.Checking whether training labels are consistent across different human annotators
Why B: Cross-validation is a resampling technique used to evaluate machine learning models by partitioning the original dataset into k equal-sized folds. The model is trained on k-1 folds and validated on the remaining fold, repeating this process k times so each fold serves as the validation set once. This provides a more robust and less biased estimate of model performance compared to a single train-test split, especially when data is limited.
Variation 2. What is cross-validation in machine learning?
medium- A.Training multiple different models and comparing their performance
- ✓ B.Repeatedly training and evaluating the model on different data splits for reliable performance estimates
- C.Checking if a model works correctly by running it backward
- D.Training a model on two different datasets simultaneously
Why B: Cross-validation is a technique for assessing how a machine learning model will generalize to an independent dataset. It involves partitioning the data into complementary subsets, training the model on one subset (the training fold), and validating it on the remaining subset (the validation fold), then repeating this process multiple times with different partitions. The final performance estimate is the average of the validation scores, which provides a more reliable and less biased measure than a single train-test split.
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.