Databricks Certified Professional Data Scientist Exam - Topic 5 Question 70 Discussion

Actual exam question for Databricks's Databricks Certified Professional Data Scientist exam

Question #: 70
Topic #: 5

[All Databricks Certified Professional Data Scientist Questions]

Refer to Exhibit

In the exhibit, the x-axis represents the derived probability of a borrower defaulting on a loan. Also in the exhibit, the pink represents borrowers that are known to have not defaulted on their loan, and the blue represents borrowers that are known to have defaulted on their loan. Which analytical method could produce the probabilities needed to build this exhibit?

ALinear Regression

BLogistic Regression

CDiscriminant Analysis

DAssociation Rules

Show Suggested Answer

Suggested Answer: B

by Amina at Sep 13, 2024, 12:55 PM

Limited Time Offer

25%

Off

Get Premium Databricks Certified Professional Data Scientist Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Belen

3 months ago

Surprised that Logistic Regression is the answer, seems too simple!

upvoted 0 times

...

Dorothea

3 months ago

Wait, are we sure it’s not Association Rules?

upvoted 0 times

...

Hannah

3 months ago

No way, it's gotta be Linear Regression.

upvoted 0 times

...

Beatriz

4 months ago

I think Discriminant Analysis could work too.

upvoted 0 times

...

Laticia

4 months ago

Definitely Logistic Regression for this!

upvoted 0 times

...

Lyda

4 months ago

Association rules don't seem to fit this context, but I can't recall the exact differences between linear and logistic regression right now.

upvoted 0 times

...

Britt

4 months ago

I practiced a similar question where logistic regression was the answer for predicting probabilities. I feel confident it's the same here.

upvoted 0 times

...

Stephane

4 months ago

I'm not entirely sure, but I think discriminant analysis might also be relevant since it deals with classifying observations.

upvoted 0 times

...

Andree

5 months ago

I remember we discussed how logistic regression is often used for binary outcomes like loan defaults. It seems like the right choice here.

upvoted 0 times

...

Fletcher

5 months ago

Logistic regression seems like the way to go here. The exhibit is showing the probability of default, which is exactly what logistic regression is designed to model.

upvoted 0 times

...

Rebbecca

5 months ago

Linear regression could work, but since the target variable is binary (default or not), logistic regression would probably be more appropriate.

upvoted 0 times

...

Leonardo

5 months ago

Hmm, the exhibit shows a probability distribution, so I'm thinking discriminant analysis might be a good fit here to classify the borrowers.

upvoted 0 times

...

Francoise

5 months ago

This looks like a classic binary classification problem. I'd approach it using logistic regression to model the probability of default.

upvoted 0 times

...

Iluminada

5 months ago

Association rules? I'm not sure that would be the best approach for this type of problem. I'd lean more towards a supervised learning method like logistic regression.

upvoted 0 times

...

Wade

5 months ago

This seems like a straightforward question about common medical symptoms. I'll start by thinking through the options and seeing which one best fits the description of chronic soreness and fatigue.

upvoted 0 times

...

Kathrine

10 months ago

I'm just glad they didn't include 'Tarot Cards' as an option. That would have really thrown me for a loop!

upvoted 0 times

Venita

8 months ago

I believe Discriminant Analysis could also work in this scenario.

upvoted 0 times

...

Iluminada

8 months ago

C) Discriminant Analysis

upvoted 0 times

...

Caprice

9 months ago

I would go with Linear Regression for this one.

upvoted 0 times

...

Valda

9 months ago

A) Linear Regression

upvoted 0 times

...

Rosamond

9 months ago

I think Logistic Regression would be the best method for this.

upvoted 0 times

...

Cecil

9 months ago

B) Logistic Regression

upvoted 0 times

...

Asuncion

10 months ago

Linear Regression? Really? The data is clearly binary, not continuous. Looks like someone in the question writing team needs a refresher on machine learning methods. *shakes head*

upvoted 0 times

Celestine

9 months ago

B) Logistic Regression

upvoted 0 times

...

Annamae

9 months ago

C) Discriminant Analysis

upvoted 0 times

...

Donette

10 months ago

B) Logistic Regression

upvoted 0 times

...

Shayne

10 months ago

Hold up, did they really think Association Rules would be a valid answer? That's like trying to solve a calculus problem with a hammer. Gotta love these exam questions, they really keep you on your toes!

upvoted 0 times

Glory

8 months ago

Who knows, maybe just to throw people off.

upvoted 0 times

...

Soledad

8 months ago

I wonder why they included it as an option.

upvoted 0 times

...

Mari

8 months ago

Definitely, it doesn't really fit the context at all.

upvoted 0 times

...

Lauran

8 months ago

Yeah, Association Rules seems like a strange choice for this exhibit.

upvoted 0 times

...

Winfred

8 months ago

D) Association Rules

upvoted 0 times

...

Emiko

8 months ago

C) Discriminant Analysis

upvoted 0 times

...

Jaime

9 months ago

B) Logistic Regression

upvoted 0 times

...

Sage

9 months ago

A) Linear Regression

upvoted 0 times

...

Glendora

11 months ago

I'm not sure about this one. Discriminant Analysis could also work, but the probabilities on the x-axis make me think Logistic Regression is the way to go. Either way, this is a tough question!

upvoted 0 times

Willard

9 months ago

I agree, the probabilities on the x-axis point towards Logistic Regression.

upvoted 0 times

...

Chauncey

9 months ago

I think Logistic Regression is the best choice here.

upvoted 0 times

...

Keneth

11 months ago

I'm not sure, but I think Logistic Regression makes sense because it can predict probabilities.

upvoted 0 times

...

Jamal

11 months ago

Logistic Regression seems like the obvious choice here. The x-axis shows probabilities, and the colors represent the two classes - defaulted and not defaulted. Logistic Regression is perfect for this kind of binary classification problem.

upvoted 0 times