nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #69

You work for a large hotel chain and have been asked to assist the marketing team in gathering predictions for a targeted marketing strategy. You need to make predictions about user lifetime value…

The correct answer is D. Submit the data for training without performing any manual transformations. AutoML Tables automatically performs feature engineering and transformations, including handling time-based signals spread across multiple columns. The platform natively understands temporal data patterns without requiring manual transformation. Manually combining time signal…

Submitted by renata2k· Apr 18, 2026Data processing and feature engineering

Question

You work for a large hotel chain and have been asked to assist the marketing team in gathering predictions for a targeted marketing strategy. You need to make predictions about user lifetime value (LTV) over the next 20 days so that marketing can be adjusted accordingly. The customer dataset is in BigQuery, and you are preparing the tabular data for training with AutoML Tables. This data has a time signal that is spread across multiple columns. How should you ensure that AutoML fits the best model to your data?

Options

  • AManually combine all columns that contain a time signal into an array.
  • BSubmit the data for training without performing any manual transformations.
  • CSubmit the data for training without performing any manual transformations, and indicate an
  • DSubmit the data for training without performing any manual transformations.

How the community answered

(46 responses)
  • A
    4% (2)
  • B
    13% (6)
  • C
    9% (4)
  • D
    74% (34)

Explanation

AutoML Tables automatically performs feature engineering and transformations, including handling time-based signals spread across multiple columns. The platform natively understands temporal data patterns without requiring manual transformation. Manually combining time signal columns into an array (A) is unnecessary and could actually reduce model quality by obscuring the individual time signals. The key insight is that AutoML Tables is designed to handle this complexity automatically, so the best approach is to submit the data as-is and let the platform determine the optimal transformations for fitting the model.

Topics

#AutoML Tables#Feature Engineering#Temporal Data#LTV Prediction

Community Discussion

No community discussion yet for this question.

Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice