You are solving a classification task. You must evaluate your model on a limited data sample by using k-fold cross-validation. You start by configuring a k parameter as the number of splits. You…

The correct answer is B. k=10. In k-fold cross-validation, k must be a positive integer greater than 1. Options k=0.5 and k=0.9 are invalid because k must be a whole number. k=1 is invalid because it would mean one fold with no held-out validation set, making cross-validation meaningless. k=10 is a valid…

Explore data and run experiments

Question

You are solving a classification task. You must evaluate your model on a limited data sample by using k-fold cross-validation. You start by configuring a k parameter as the number of splits. You need to configure the k parameter for the cross-validation. Which value should you use?

Options

Ak=1
Bk=10
Ck=0.5
Dk=0.9

How the community answered

(54 responses)

A
4% (2)
B
94% (51)
D
2% (1)

Explanation

In k-fold cross-validation, k must be a positive integer greater than 1. Options k=0.5 and k=0.9 are invalid because k must be a whole number. k=1 is invalid because it would mean one fold with no held-out validation set, making cross-validation meaningless. k=10 is a valid, widely used standard value: the dataset is divided into 10 equal folds, the model is trained 10 times (each time using 9 folds for training and 1 fold for validation), and performance is averaged across all 10 runs. k=10 provides a reliable estimate of generalization performance with acceptable computational cost.

Topics

#Cross-validation#Model evaluation#K-fold cross-validation

Community Discussion

No community discussion yet for this question.

Full DP-100 Practice