Machine Learning Specialist is building a model to predict future employment rates based on a wide range of economic factors. While exploring the data, the Specialist notices that the magnitude of…

Question

Options

• AApply quantile binning to group the data into categorical bins to keep any relationships in the data
• BApply the Cartesian product transformation to create new combinations of fields that are
• CApply normalization to ensure each field will have a mean of 0 and a variance of 1 to remove any
• DApply the orthogonal sparse bigram (OSB) transformation to apply a fixed-size sliding window to

• A
  5% (1)
• B
  5% (1)
• C
  82% (18)
• D
  9% (2)

Explanation

When input features have vastly different magnitudes, models that rely on distances or gradient-based optimization (including linear and logistic regression) will be biased toward high-magnitude features simply due to scale, not importance. Normalization (specifically standardization: subtracting the mean and dividing by the standard deviation to achieve mean=0 and variance=1) (C) rescales all features to a common scale, eliminating magnitude bias while preserving the relative relationships and distribution within each feature. This ensures each feature contributes proportionally based on its actual predictive value. Quantile binning (A) converts continuous data to categorical bins, destroying the numerical relationships needed for regression. The Cartesian product transformation (B) generates new feature combinations and is unrelated to scaling. The orthogonal sparse bigram (OSB) transformation (D) is a text feature engineering technique, not a numerical scaling method.

No community discussion yet for this question.