Snowflake DSA-C02 Exam - Topic 1 Question 3 Discussion

Actual exam question for Snowflake's DSA-C02 exam

Question #: 3
Topic #: 1

[All DSA-C02 Questions]

You are training a binary classification model to support admission approval decisions for a college degree program.

How can you evaluate if the model is fair, and doesn't discriminate based on ethnicity?

AEvaluate each trained model with a validation dataset and use the model with the highest accuracy score.

BRemove the ethnicity feature from the training dataset.

CCompare disparity between selection rates and performance metrics across ethnicities.

DNone of the above.

Show Suggested Answer

Suggested Answer: C

By using ethnicity as a sensitive field, and comparing disparity between selection rates and performance metrics for each ethnicity value, you can evaluate the fairness of the model.

by Andra at Oct 02, 2023, 12:47 PM

Limited Time Offer

25%

Off

Get Premium DSA-C02 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Karan

6 months ago

D seems like a cop-out. We need better options!

upvoted 0 times

...

Serina

6 months ago

Wait, removing ethnicity might hide issues, right?

upvoted 0 times

...

Reena

6 months ago

A is not enough, accuracy doesn't mean fairness.

upvoted 0 times

...

Eva

7 months ago

Totally agree with C! Disparity analysis is key.

upvoted 0 times

...

Larae

7 months ago

C is the way to go! Gotta check those selection rates.

upvoted 0 times

...

Lettie

7 months ago

I’m a bit confused about this one. I feel like none of the options fully address the fairness issue.

upvoted 0 times

...

Ashton

7 months ago

Comparing selection rates across different ethnicities sounds familiar; I think that might be the right approach to ensure fairness.

upvoted 0 times

...

Micah

7 months ago

I think removing the ethnicity feature might help, but it feels like it could just mask the problem instead of solving it.

upvoted 0 times

...

Buck

8 months ago

I remember we discussed evaluating models for fairness, but I'm not sure if just looking at accuracy is enough.

upvoted 0 times

...

Ora

8 months ago

Ah, I see. Comparing the selection rates and performance across ethnicities is probably the way to go to really assess if the model is fair. That's the approach I'll focus on.

upvoted 0 times

...

Pamella

8 months ago

I'm a bit confused on this one. I'll need to review the concepts of model fairness and discrimination more carefully before deciding.

upvoted 0 times

...

Jose

8 months ago

Removing the ethnicity feature seems like the simplest solution, but I'm not sure if that's really the best way to evaluate fairness.

upvoted 0 times

...

Michael

8 months ago

Okay, I've got a few ideas here. I'm leaning towards comparing the performance metrics across different ethnicities to check for any unfair biases.

upvoted 0 times

...

Margurite

8 months ago

Hmm, this is a tricky one. I think I'll need to really think through the different approaches and their pros and cons.

upvoted 0 times

...

Wilbert

8 months ago

I'm a bit confused on this one. Is the first fetch supposed to be manually triggered? That's not something I was aware of, so I'll need to double-check that.

upvoted 0 times

...

Geraldine

8 months ago

This looks straightforward enough. I'm confident I can put together the right UPDATE statement to meet all the requirements. I'll just need to pay close attention to the details.

upvoted 0 times

...

Erinn

8 months ago

Okay, I've got a strategy in mind. I'll analyze the question, consider the Agile Scrum framework, and then select the option that seems most likely to drive a successful transformation.

upvoted 0 times

...