A single gondola departure_at string hides hour-of-day and weekday that a no-show model needs. Which feature-engineering technique should they apply?
Select an answer to reveal the explanation.
Short Explanation
Think of a single departure_at string hiding hour-of-day and weekday. Split that composite datetime into model-usable parts. Feeding the raw string to a linear trainer skips the signal.
Full Explanation
Feature splitting turns a composite field such as a datetime or address into model-usable parts. Feeding the raw string, calling it a storage class, and Polly do not extract hour and weekday.