Quick Answer
The answer is tracking prediction distribution across demographic segments. This metric directly monitors model bias and fairness by comparing the rate at which the model assigns positive outcomes to different protected groups, revealing potential disparate impact if the distributions diverge significantly. On the Google Professional Data Engineer exam, this concept tests your understanding of algorithmic fairness in MLOps—specifically that monitoring prediction distribution goes beyond operational metrics like accuracy or latency to catch subtle bias drift. A common trap is confusing this with monitoring feature distribution or input data skew; while those are important, they do not directly measure whether the model’s outputs themselves are unfairly balanced. Remember the memory tip: “Outputs, not inputs” – for fairness, you watch what the model predicts, not just what it receives. This aligns with the exam’s emphasis on responsible AI practices in production environments.
This PDE practice question tests your understanding of operationalizing machine learning models. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A financial services company must ensure that predictions from a deployed model do not become biased against protected groups. They have a monitoring system in place. Which metric should they track?
Prediction latency
Why wrong: Latency is a performance metric, not a fairness metric.
Prediction distribution across demographic segments
Comparing prediction distributions across groups reveals potential bias in outcomes.
Per-query input feature distribution
Why wrong: Input feature distribution identifies drift but not outcome bias.
Model accuracy over time
Why wrong: Accuracy does not capture bias; a model can be accurate but biased.
Answer choices
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Prediction distribution across demographic segments
Tracking prediction distribution across demographic segments (option B) directly monitors for bias by comparing the model's output rates for different protected groups. If the distribution diverges significantly, it indicates potential disparate impact, which is the core concern for fairness in deployed models. This aligns with monitoring for algorithmic fairness, not just operational performance.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
For each option: why learners choose it and why it is or isn't the right answer here.
Prediction latency
Why it's wrong here
Latency is a performance metric, not a fairness metric.
Prediction distribution across demographic segments
Why this is correct
Comparing prediction distributions across groups reveals potential bias in outcomes.
Related concept
Read the scenario before looking for a memorised answer.
Per-query input feature distribution
Why it's wrong here
Input feature distribution identifies drift but not outcome bias.
Model accuracy over time
Why it's wrong here
Accuracy does not capture bias; a model can be accurate but biased.
Common exam traps
The trap here is that candidates confuse operational metrics (latency, accuracy) with fairness metrics, assuming high accuracy guarantees fairness, but Cisco tests that bias can exist even with high accuracy if the model performs differently across demographic segments.
Detailed technical explanation
Under the hood, bias monitoring often uses statistical parity or equal opportunity metrics, comparing the prediction rates (e.g., positive outcome rate) across demographic groups defined by protected attributes. A common subtlety is Simpson's paradox, where overall accuracy looks fine but subgroup accuracy reveals bias; tracking distribution per segment catches this. In practice, tools like Google's What-If Tool or AWS SageMaker Clarify compute these distributions automatically to flag drift in fairness metrics.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
What to study next
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Operationalizing machine learning models — study guide chapter
Learn the concepts, then practise the questions
Operationalizing machine learning models practice questions
Targeted practice on this topic area only
All PDE questions
499 questions across all exam domains
Google Professional Data Engineer study guide
Full concept coverage aligned to exam objectives
PDE practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Practise PDE questions linked to Designing data processing systems.
Practise PDE questions linked to Building and operationalizing data processing systems.
Practise PDE questions linked to Operationalizing machine learning models.
Practise PDE questions linked to Ensuring solution quality.
Practise PDE questions linked to PDE fundamentals.
Practise PDE questions linked to PDE scenario.
Practise PDE questions linked to PDE troubleshooting.
Practice this exam
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Operationalizing machine learning models — This question tests Operationalizing machine learning models — Read the scenario before looking for a memorised answer..
The correct answer is: Prediction distribution across demographic segments — Tracking prediction distribution across demographic segments (option B) directly monitors for bias by comparing the model's output rates for different protected groups. If the distribution diverges significantly, it indicates potential disparate impact, which is the core concern for fairness in deployed models. This aligns with monitoring for algorithmic fairness, not just operational performance.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Last reviewed: Jun 24, 2026
This PDE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PDE exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.