nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #151

You work for a retailer that sells clothes to customers around the world. You have been tasked with ensuring that ML models are built in a secure manner. Specifically, you need to protect sensitive cu

The correct answer is A. Tokenize all of the fields using hashed dummy values to replace the real values.. Tokenization with hashed dummy values replaces actual sensitive field values with consistent, irreversible tokens, ensuring the raw PII (e.g., exact age, exact location coordinates) is never exposed to the data science team. The tokens remain consistent (same input always maps to

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

Question

You work for a retailer that sells clothes to customers around the world. You have been tasked with ensuring that ML models are built in a secure manner. Specifically, you need to protect sensitive customer data that might be used in the models. You have identified four fields containing sensitive data that are being used by your data science team: AGE, IS_EXISTING_CUSTOMER, LATITUDE_LONGITUDE, and SHIRT_SIZE. What should you do with the data before it is made available to the data science team for training purposes?

Options

  • ATokenize all of the fields using hashed dummy values to replace the real values.
  • BUse principal component analysis (PCA) to reduce the four sensitive fields to one PCA vector.
  • CCoarsen the data by putting AGE into quantiles and rounding LATITUDE_LONGTTUDE into
  • DRemove all sensitive data fields, and ask the data science team to build their models using non-

How the community answered

(30 responses)
  • A
    83% (25)
  • B
    10% (3)
  • C
    3% (1)
  • D
    3% (1)

Explanation

Tokenization with hashed dummy values replaces actual sensitive field values with consistent, irreversible tokens, ensuring the raw PII (e.g., exact age, exact location coordinates) is never exposed to the data science team. The tokens remain consistent (same input always maps to the same token), so they can still be used as categorical features in ML models. Option B (PCA) mathematically transforms but does not hide the underlying data. Option C (coarsening) reduces precision but still exposes approximate real values and may not meet security/compliance requirements. Option D (removing all fields) eliminates potentially predictive features unnecessarily.

Topics

#Data Security#Privacy-Preserving ML#Data Anonymization#Data Preprocessing

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice