A city government is building a model to predict traffic congestion. They have sensor data from highways and local roads. The data is heavily skewed toward highways, which have more sensors. What sampling strategy should they use to ensure the model works well for all road types?

Oversampling local roads to match highway count

Stratified sampling by road type

Systematic sampling every 10th record

Random sampling from the entire dataset

A startup is building a computer vision model to detect defects on a production line. They have 500 labeled images per defect type. The model is a deep convolutional neural network. What should they do to ensure sufficient data volume?

Use a simpler model that requires less data

Collect more images and apply data augmentation techniques

Use the 500 images per class as-is, since deep learning models work well with small datasets

Reduce the number of defect classes to increase samples per class

What is the primary factor that determines the minimum data volume needed to train a reliable AI model?

The storage capacity of the training environment

The model's complexity and the performance goals

The number of developers on the team

What does 'granularity' refer to in the context of data requirements for AI training?

The number of features in the dataset

The accuracy of the data values

The file format used to store the data

The level of detail or aggregation in the data

PMICertified Professional in Managing AI (PMI-CPMAI)

Domain 3Objective 1

Define Required Data PMI-CPMAI Practice Questions (Page 1)

Part of the Identify Data Needs domain, which accounts for 26% of the PMI-CPMAI exam. PMI does not publish an official question count, but from its 160-minute exam (~65–105 total, ~17–27 in this domain), expect 2–3 from this objective — we provide 33 practice questions to prepare you well beyond it. (estimate)

33questions here

7free pages

9concepts

26%of the exam

Questions 1–5

1application · medium
A city government is building a model to predict traffic congestion. They have sensor data from highways and local roads. The data is heavily skewed toward highways, which have more sensors. What sampling strategy should they use to ensure the model works well for all road types?
Select an answer first
2application · medium
A startup is building a computer vision model to detect defects on a production line. They have 500 labeled images per defect type. The model is a deep convolutional neural network. What should they do to ensure sufficient data volume?
Select an answer first
3foundation · easy
Which data format is most appropriate for storing a collection of customer reviews where each review has variable length and no fixed schema?
Select an answer first
4foundation · easy
What is the primary factor that determines the minimum data volume needed to train a reliable AI model?
Select an answer first
5foundation · easy
What does 'granularity' refer to in the context of data requirements for AI training?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to PMI-CPMAI

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by PMI. “PMI-CPMAI” is a trademark of its owner, used for identification only.