New Year Sale 2026! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions
Mail Us support@pass4success.com
Location US
Mob_nav_barsMENU

Microsoft DP-100 Exam - Topic 4 Question 128 Discussion

Actual exam question for Microsoft's DP-100 exam
Question #: 128
Topic #: 4
[All DP-100 Questions]

You are building a binary classification model by using a supplied training set.

The training set is imbalanced between two classes.

You need to resolve the data imbalance.

What are three possible ways to achieve this goal? Each correct answer presents a complete solution NOTE: Each correct selection is worth one point.

Show Suggested Answer Hide Answer
Suggested Answer: A, B, D

https://machinelearningmastery.com/tactics-to-combat-imbalanced-classes-in-your-machine-learning-dataset/

by Maurine at Jul 08, 2025, 03:41 PM

Limited Time Offer

25%

Off

Get Premium DP-100 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

0/2000 characters
Submit Cancel
Quentin
2 months ago
Wait, can resampling really fix the imbalance issue? Sounds too easy.
upvoted 0 times
...
Noelia
3 months ago
Using accuracy as a metric? That's a bad idea for imbalanced data.
upvoted 0 times
...
Myra
3 months ago
Generating synthetic samples is a great strategy!
upvoted 0 times
...
Patrick
3 months ago
I think penalizing the classification can help too.
upvoted 0 times
...
Annett
3 months ago
Resampling is a solid choice!
upvoted 0 times
...
Alysa
4 months ago
I feel like using accuracy as an evaluation metric isn't a good idea for imbalanced datasets, but I can't remember what we should use instead.
upvoted 0 times
...
Lili
4 months ago
Generating synthetic samples for the minority class sounds right, but I can't recall the exact method we discussed. Was it SMOTE or something else?
upvoted 0 times
...
Lisha
4 months ago
I think resampling the dataset is definitely one way to handle imbalance, either by undersampling or oversampling. That seems familiar.
upvoted 0 times
...
Lisandra
4 months ago
I remember we talked about penalizing the classification to help with imbalanced data, but I'm not sure if that's a complete solution.
upvoted 0 times
...
Luz
4 months ago
I'm a little confused by this question. Is normalizing the feature set (option E) really a way to handle class imbalance? I was thinking that would be more for improving model performance in general. I'm leaning towards options B and C, but I'll have to double-check my understanding before answering.
upvoted 0 times
...
Virgie
5 months ago
Okay, I've got this! The key here is to not use accuracy as the evaluation metric, since that can be misleading with imbalanced data. I'll go with options B and C - resampling and generating synthetic samples. That should help balance out the classes and give me a more reliable model.
upvoted 0 times
...
Barbra
5 months ago
Hmm, I'm a bit unsure about this one. I know we need to address the class imbalance, but I'm not sure if penalizing the classification (option A) is a good approach. I'll have to think more about the pros and cons of the different options before deciding.
upvoted 0 times
...
Una
5 months ago
This looks like a straightforward question on handling imbalanced datasets. I think I'll go with options B and C - resampling the data using under/oversampling, and generating synthetic samples for the minority class. Those seem like the most common and effective techniques for this problem.
upvoted 0 times
...
Johna
7 months ago
Wait, did they just throw in a completely irrelevant option just to mess with us? D, really? Accuracy? What is this, amateur hour?
upvoted 0 times
...
Javier
7 months ago
A, penalizing the classification? Sounds like a good idea, but I'm not sure how that would work in practice. Hmm, maybe I need to read up on that one.
upvoted 0 times
Helga
5 months ago
C) Generate synthetic samples in the minority class.
upvoted 0 times
...
Lewis
5 months ago
B) Resample the data set using under sampling or oversampling
upvoted 0 times
...
Rosendo
6 months ago
A) Penalize the classification
upvoted 0 times
...
...
Elvis
7 months ago
E? Normalize the features? What is this, a trick question? That's got nothing to do with class imbalance.
upvoted 0 times
Ernest
5 months ago
A) Penalize the classification
upvoted 0 times
...
...
Stephanie
7 months ago
I believe generating synthetic samples in the minority class could also be a good solution.
upvoted 0 times
...
Lucina
8 months ago
Definitely not D. Accuracy is a terrible metric for imbalanced data. You gotta use something like F1-score or area under the ROC curve.
upvoted 0 times
Delmy
7 months ago
C) Generate synthetic samples in the minority class.
upvoted 0 times
...
Willow
7 months ago
B) Resample the data set using under sampling or oversampling
upvoted 0 times
...
Tresa
7 months ago
A) Penalize the classification
upvoted 0 times
...
...
Nickolas
8 months ago
B and C are the way to go! Oversampling and synthetic samples are classic techniques for imbalanced datasets.
upvoted 0 times
Raelene
7 months ago
Using accuracy as the evaluation metric may not be suitable for imbalanced datasets.
upvoted 0 times
...
Felicitas
7 months ago
Penalizing the classification can also help in balancing the classes.
upvoted 0 times
...
Deangelo
8 months ago
I agree, oversampling and generating synthetic samples are effective methods for handling imbalanced data.
upvoted 0 times
...
...
Paris
8 months ago
I agree with Linsey. Resampling the data set can help balance the classes.
upvoted 0 times
...
Linsey
8 months ago
I think we should resample the data set using under sampling or oversampling.
upvoted 0 times
...

Save Cancel