PLS identifies new features in a supervised way by relating them to the target variable.

PLS identifies new features in a supervised way by relating them to the target variable.

• A. True
• B. False
• C. It is unsupervised
• D. It does not use the target variable

Answer: (A)

PLS is a supervised dimension-reduction method that creates latent features by relating them to the target variable. It builds new components as linear combinations of the original predictors in a way that the resulting scores align with the response, typically by maximizing the covariance between the predictor scores and the target. This means the extracted features are chosen specifically because they are most informative for predicting the target, which is the hallmark of a supervised approach. This contrasts with unsupervised methods like PCA, which form components based only on the structure and variance in the predictors without reference to the outcome. In PLS, the target variable guides the feature extraction, so the new features (the latent components) are designed to be predictive of the response.

PLS is a supervised dimension-reduction method that creates latent features by relating them to the target variable. It builds new components as linear combinations of the original predictors in a way that the resulting scores align with the response, typically by maximizing the covariance between the predictor scores and the target. This means the extracted features are chosen specifically because they are most informative for predicting the target, which is the hallmark of a supervised approach.

This contrasts with unsupervised methods like PCA, which form components based only on the structure and variance in the predictors without reference to the outcome. In PLS, the target variable guides the feature extraction, so the new features (the latent components) are designed to be predictive of the response.