MLS-C01 · Question #90
A credit card company wants to build a credit scoring model to help predict whether a new credit card applicant will default on a credit card payment. The company has collected data from a large…
The correct answer is C. Use an autoencoder or principal component analysis (PCA) to replace original features with new. PCA (Principal Component Analysis) and autoencoders are dimensionality reduction techniques that transform the original high-dimensional, correlated feature space into a smaller set of uncorrelated components (principal components) that still capture most of the variance. This…
Question
A credit card company wants to build a credit scoring model to help predict whether a new credit card applicant will default on a credit card payment. The company has collected data from a large number of sources with thousands of raw attributes. Early experiments to train a classification model revealed that many attributes are highly correlated, the large number of features slows down the training speed significantly, and that there are some overfitting issues. The Data Scientist on this project would like to speed up the model training time without losing a lot of information from the original dataset. Which feature engineering technique should the Data Scientist use to meet the objectives?
Options
- ARun self-correlation on all features and remove highly correlated features
- BNormalize all numerical values to be between 0 and 1
- CUse an autoencoder or principal component analysis (PCA) to replace original features with new
- DCluster raw data using k-means and use sample data from each cluster to build a new dataset
How the community answered
(36 responses)- A8% (3)
- B14% (5)
- C75% (27)
- D3% (1)
Explanation
PCA (Principal Component Analysis) and autoencoders are dimensionality reduction techniques that transform the original high-dimensional, correlated feature space into a smaller set of uncorrelated components (principal components) that still capture most of the variance. This directly addresses all three problems: (1) reduces the number of features, speeding up training; (2) removes multicollinearity by creating orthogonal components; and (3) reduces overfitting by constraining the model's complexity. Removing correlated features (A) is less systematic and loses information. Normalization (B) only rescales values without reducing dimensions. K-means clustering (D) is for grouping observations, not for reducing feature space.
Topics
Community Discussion
No community discussion yet for this question.