nerdexam
Microsoft

DP-100 · Question #116

Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might…

The correct answer is B. No. Stratified split does not compensate for class imbalance - it preserves the existing class distribution across the train/test split rather than correcting it. If the original dataset has a 95/5 class ratio, a stratified split will produce subsets with the same 95/5 ratio. To…

Design and prepare a machine learning solution

Question

Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution. After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen. You are creating a new experiment in Azure Machine Learning Studio. One class has a much smaller number of observations than the other classes in the training set. You need to select an appropriate data sampling strategy to compensate for the class imbalance. Solution: You use the Stratified split for the sampling mode. Does the solution meet the goal?

Options

  • AYes
  • BNo

How the community answered

(43 responses)
  • A
    28% (12)
  • B
    72% (31)

Explanation

Stratified split does not compensate for class imbalance - it preserves the existing class distribution across the train/test split rather than correcting it. If the original dataset has a 95/5 class ratio, a stratified split will produce subsets with the same 95/5 ratio. To actually address class imbalance, you would use techniques such as SMOTE (Synthetic Minority Over-sampling Technique), random oversampling of the minority class, random undersampling of the majority class, or class weighting during model training. The solution does not meet the goal.

Topics

#Class Imbalance#Data Sampling#Stratified Splitting#Azure Machine Learning

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full DP-100 Practice