Deal of The Day! 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

CertNexus AIP-210 Exam - Topic 1 Question 28 Discussion

Actual exam question for CertNexus's AIP-210 exam
Question #: 28
Topic #: 1
[All AIP-210 Questions]

You have a dataset with thousands of features, all of which are categorical. Using these features as predictors, you are tasked with creating a prediction model to accurately predict the value of a continuous dependent variable. Which of the following would be appropriate algorithms to use? (Select two.)

Show Suggested Answer Hide Answer
Suggested Answer: C, E

Lasso regression and ridge regression are both types of linear regression models that can handle high-dimensional and categorical data. They use regularization techniques to reduce the complexity of the model and avoid overfitting. Lasso regression uses L1 regularization, which adds a penalty term proportional to the absolute value of the coefficients to the loss function. This can shrink some coefficients to zero and perform feature selection. Ridge regression uses L2 regularization, which adds a penalty term proportional to the square of the coefficients to the loss function. This can shrink all coefficients towards zero and reduce multicollinearity. Reference: [Lasso (statistics) - Wikipedia], [Ridge regression - Wikipedia]


by Cammy at Sep 17, 2024, 07:33 PM

Limited Time Offer

25%

Off

Get Premium AIP-210 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

0/2000 characters
Submit Cancel
Evangelina
5 months ago
K-means? That doesn't fit this scenario at all!
upvoted 0 times
...
Juliana
5 months ago
Lasso regression could be useful too, right?
upvoted 0 times
...
Lauran
5 months ago
Wait, isn't logistic regression for classification only?
upvoted 0 times
...
Refugia
6 months ago
Totally agree, those work well with categorical data.
upvoted 0 times
...
Willow
6 months ago
K-nearest neighbors and Ridge regression are solid choices!
upvoted 0 times
...
Gerald
6 months ago
Logistic regression seems off since it's for classification, but I wonder if K-nearest neighbors is the best option alongside Ridge.
upvoted 0 times
...
Jesusita
6 months ago
I think Ridge regression might be a good choice here, but I can't recall if it specifically requires numerical features.
upvoted 0 times
...
Celeste
6 months ago
I feel like K-nearest neighbors could work since it can handle categorical data, but I'm not sure about Lasso regression.
upvoted 0 times
...
Lynda
6 months ago
I remember we discussed that K-means is more for clustering, so I don't think that's right for predicting a continuous variable.
upvoted 0 times
...
Gerri
6 months ago
I'm a bit confused here. Logistic regression is typically used for binary classification, not continuous prediction. I'm not sure that would be the best fit for this problem. I think I'll go with Lasso and Ridge regression as the two most appropriate options.
upvoted 0 times
...
Helene
6 months ago
Okay, let's think this through. We need an algorithm that can handle continuous dependent variables, not categorical ones. So I'm going to rule out K-means and K-nearest neighbors since those are more for clustering. I'll go with Lasso and Ridge regression.
upvoted 0 times
...
Penney
7 months ago
Hmm, this is a tricky one. With thousands of categorical features, I'd want to use an algorithm that can handle that kind of high-dimensional data. I'm thinking Lasso regression and Ridge regression might be good options to try.
upvoted 0 times
...
Wilda
7 months ago
This seems straightforward to me. With thousands of categorical features, we'll want to use a regularized regression technique like Lasso or Ridge to avoid overfitting. Those are the two algorithms I'd select for this type of predictive modeling task.
upvoted 0 times
...
Thaddeus
7 months ago
The TimeoutMS property seems like it could be useful, but I'm not sure if that's the best way to handle activity failures. I'll need to double-check the details on how each of these options work.
upvoted 0 times
...
Bong
2 years ago
Wait, I thought K-means was for clustering, not prediction. Maybe I should have paid more attention in class.
upvoted 0 times
...
Jani
2 years ago
Logistic regression? For a continuous dependent variable? I think someone needs to go back to Stats 101.
upvoted 0 times
...
Chandra
2 years ago
C and E are the way to go. Gotta love that L1 and L2 regularization.
upvoted 0 times
...
Craig
2 years ago
K-nearest neighbors? Really? That's like using a hammer to fix a computer.
upvoted 0 times
Kristin
1 year ago
E) Ridge regression
upvoted 0 times
...
Argelia
1 year ago
D) Logistic regression
upvoted 0 times
...
Craig
2 years ago
A) K-means
upvoted 0 times
...
...
Chantay
2 years ago
I would also consider using K-nearest neighbors for this task.
upvoted 0 times
...
Miesha
2 years ago
I agree with Antonio. Logistic regression is suitable for categorical features.
upvoted 0 times
...
Antonio
2 years ago
I think logistic regression would be a good choice.
upvoted 0 times
...
Tawny
2 years ago
I think Lasso regression and Ridge regression would be the best choices here. With so many categorical features, we need some form of regularization to avoid overfitting.
upvoted 0 times
Gladis
1 year ago
I think using Lasso and Ridge regression is a good idea to prevent overfitting.
upvoted 0 times
...
Paola
2 years ago
Logistic regression could be useful for binary classification.
upvoted 0 times
...
Annice
2 years ago
K-means and K-nearest neighbors wouldn't work well with categorical features.
upvoted 0 times
...
Ulysses
2 years ago
I agree, Lasso and Ridge regression would help with regularization.
upvoted 0 times
...
...

Save Cancel