A data scientist is working with a dataset of 500 features for a customer segmentation task using k-means clustering. The features are highly correlated and contain redundant information. The scientist wants to reduce dimensionality while preserving the variance structure for clustering. Which approach is most appropriate?

Apply an autoencoder and use the bottleneck layer as the reduced representation.

Apply PCA and keep the number of components that explains 95% of the variance.

Use a filter method to select the 50 features with the highest variance.

Apply t-SNE to reduce to 2 dimensions and cluster on the output.

A data scientist is building a logistic regression model with 1,000 features but only 2,000 training samples. The goal is to select a subset of features that maximizes predictive performance while avoiding overfitting. The scientist is considering filter, wrapper, and embedded methods. Which approach is most appropriate given the small sample size?

Use L1-regularized logistic regression and select features with non-zero coefficients.

Use all 1,000 features without selection and rely on the model's regularization.

Use a wrapper method with forward selection and cross-validation.

Use a filter method selecting the top 100 features by mutual information.

What is the primary purpose of feature engineering in a machine learning workflow?

To reduce the size of the dataset by removing rows with missing values

To automatically select the best machine learning algorithm for a given dataset

To transform raw data into a format that improves model performance and interpretability

To evaluate the performance of a trained model on unseen data

Which of the following is a linear dimensionality reduction technique?

Principal Component Analysis (PCA)

SnowflakeSnowPro Advanced — Data Scientist

Domain 3Objective 2

Engineer Features for Models SNOWPRO-ADVANCED-DATA-SCIENTIST Practice Questions (Page 1)

Part of the Data Preparation and Feature Engineering domain, which makes up ~26% of our current practice bank.

45questions here

9free pages

15concepts

Questions 1–5

1expert · hard
A data scientist is working with a dataset of 500 features for a customer segmentation task using k-means clustering. The features are highly correlated and contain redundant information. The scientist wants to reduce dimensionality while preserving the variance structure for clustering. Which approach is most appropriate?
Select an answer first
2foundation · easy
Which encoding method creates binary columns for each category of a nominal variable?
Select an answer first
3expert · hard
A data scientist is building a logistic regression model with 1,000 features but only 2,000 training samples. The goal is to select a subset of features that maximizes predictive performance while avoiding overfitting. The scientist is considering filter, wrapper, and embedded methods. Which approach is most appropriate given the small sample size?
Select an answer first
4foundation · easy
What is the primary purpose of feature engineering in a machine learning workflow?
Select an answer first
5foundation · easy
Which of the following is a linear dimensionality reduction technique?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to SNOWPRO-ADVANCED-DATA-SCIENTIST

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Snowflake. “SNOWPRO-ADVANCED-DATA-SCIENTIST” is a trademark of its owner, used for identification only.

Engineer Features for Models SNOWPRO-ADVANCED-DATA-SCIENTIST Practice Questions (Page 1)

Questions 1–5

Which encoding method creates binary columns for each category of a nominal variable?

What is the primary purpose of feature engineering in a machine learning workflow?

Which of the following is a linear dimensionality reduction technique?

Keep studying — Data Preparation and Feature Engineering