pmi cpmai-v7 practice test

Clean, well-labeled datasets used for machine learning are partitioned into three subsets: Training
sets, Validation sets, and Test sets. As your team is doing this, what's the best way to split up this
data?

• A. Split by patterned subsampling
• B. Split by random subsampling
• C. Use the same data for all sets
• D. Split by alphabetical order

You need to hire a data scientist to join your team. What skill sets should you be looking for when
hiring and interviewing this person? (Select all that apply.)

• A. Prompt engineering skills
• B. Understanding of tools and technologies for manipulating, collecting, and preparing large data sets
• C. Critical thinking skills
• D. Understanding of algorithms
• E. Automation skills, especially around creating RPA bots
• F. Strong math skills, especially in calculus and statistics

Creating machine learning models can be complicated. Your team wants to use tools called
Automated Machine Learning (AutoML) to simplify the process. You know of another team that has
used AutoML tools and it's saved the team a lot of time.
However, what's the one area you should not have the AutoML tool help with?

• A. Automatic model assessment
• B. Iterative modeling and evaluation
• C. Automatic hyperparameter tuning
• D. Automatic model selection
• E. Automatic algorithm selection

One of the key elements of a data-centric methodology is the data requirements phase. During
CPMAI Phase II, several unexpected issues have developed and are now threatening the data
collection efforts.
What course of action might make the issue worse?

• A. See if you can expand the scope to continue with the project
• B. See if you already have access to enough data to continue with the project
• C. See if you can adjust the scope of this interaction to continue with the project
• D. See if you can purchase the data needed to continue with the project

You're testing your model and it is overly sensitive to the fluctuations of data and having trouble
generalizing. What type of problem is this?

• A. You are underfitting the data
• B. You are overfitting the data
• C. You have selected the wrong algorithm
• D. You have selected the wrong data

Major factors for the project you are currently working on is around the training time, cost, and
complexity of training your models. Which algorithm is not the best choice given these constraints?

• A. Support Vector Machines (SVM)
• B. Neural Networks
• C. Naive Bayes
• D. Gaussian Mixture

Your team is testing the NLP model they just created to make sure it's performing as expected. Some
of your team members want to move this model to production and move to the next iteration.
What's wrong with this workflow?

• A. You need to make sure the AI Go/No Go questions have been addressed
• B. Nothing is wrong with this workflow. You can move to the next iteration
• C. Team members should not be able to move to new projects until senior management signs off
• D. Model Evaluation requires continuous model evaluation, retraining, and operationalization

Your team is looking to develop an RPA bot to help with back-office processes such as data entry.
What type of bot should your team be creating?

• A. Unattended bot
• B. Business Process Outsourcing
• C. Attended bot
• D. RPA is not the right solution to this problem

The growth of Big Data has led to a desire to be able to do more to process and extract more value
from Big Dat
a. Simply storing data and providing analytics is no longer enough anymore to remain competitive.
To keep your organization competitive, you need to:

• A. Make sure the technical team has deep understanding of big data and how best to extract value from big data to unleash it for competitive advantage.
• B. Make sure senior management has deep understanding of big data and how best to extract value from big data to unleash it for competitive advantage.
• C. Make sure all senior leadership is data literate, understands the Vs of big data, data's connections to your specific team, and how to extract value from big data to unleash it for competitive advantage.
• D. Make sure everyone on the team has an understanding of data, its connections to the organization, and how to extract value from big data to unleash it for competitive advantage.

During CPMAI Phase II, it's important to not only understand the sources of your data but also what
data is required for training as well as identifying the features that are required.
When looking to gather data, what approach is best when determining how much data you need?

• A. The "Goldilocks" approach
• B. The "less is better" approach
• C. The "more is better" approach
• D. There is no correct approach