Google Cloud Professional Machine Learning Engineer — Question 258

You are developing a model to help your company create more targeted online advertising campaigns. You need to create a dataset that you will use to train the model. You want to avoid creating or reinforcing unfair bias in the model. What should you do? (Choose two.)

Answer options

• A. Include a comprehensive set of demographic features
• B. Include only the demographic groups that most frequently interact with advertisements
• C. Collect a random sample of production traffic to build the training dataset
• D. Collect a stratified sample of production traffic to build the training dataset
• E. Conduct fairness tests across sensitive categories and demographics on the trained model

Correct answer: D

Explanation

The correct answer, D, involves collecting a stratified sample which ensures representation across different groups, helping to minimize bias. A is not sufficient on its own, as just having demographic features doesn't ensure fairness. B is problematic because it excludes less represented groups, reinforcing bias. C, while useful in some contexts, may not ensure balanced representation needed for fairness.