Deal of The Day! Hurry Up, Grab the Special Discount - Save 25% - Ends In 0d 1h 14m 5s Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions

Microsoft Exam DP-100 Topic 2 Question 108 Discussion

Actual exam question for Microsoft's DP-100 exam
Question #: 108
Topic #: 2
[All DP-100 Questions]

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?

Show Suggested Answer Hide Answer
Suggested Answer: B

Contribute your Thoughts:

Noble
29 days ago
Wait, is k-fold cross-validation the new crypto trend? I'm going to invest all my life savings in it!
upvoted 0 times
...
Janae
1 months ago
0.9? Hmm, looks like someone's trying to game the system. Nice try, but k-fold cross-validation requires whole numbers!
upvoted 0 times
...
Sabina
1 months ago
0.5? What is this, a discount voucher? The k-value has to be a positive integer, folks!
upvoted 0 times
...
Alberto
1 months ago
10 is the way to go! It's a good balance between computational cost and model evaluation accuracy.
upvoted 0 times
Gwenn
4 days ago
D) k=0.9
upvoted 0 times
...
Sonia
5 days ago
C) k=0.5
upvoted 0 times
...
Shaun
12 days ago
B) k=10
upvoted 0 times
...
Derick
25 days ago
A) k=1
upvoted 0 times
...
...
Cyril
2 months ago
A k-value of 1 for k-fold cross-validation? Really? That's just plain old holdout validation, not cross-validation at all!
upvoted 0 times
Tonette
2 days ago
D) k=0.9
upvoted 0 times
...
Cherry
3 days ago
C) k=0.5
upvoted 0 times
...
Delmy
11 days ago
B) k=10
upvoted 0 times
...
Virgie
12 days ago
A) k=1
upvoted 0 times
...
...
Meaghan
2 months ago
I'm not sure, but I think k=10 provides a good balance between bias and variance in the model evaluation.
upvoted 0 times
...
Bette
2 months ago
I agree with Kirby, k=10 is a common choice for k-fold cross validation.
upvoted 0 times
...
Kirby
2 months ago
I think we should use k=10 for cross-validation.
upvoted 0 times
...

Save Cancel
a