10 exam-style questions with answers and explanations, straight from our 1,030-question bank. Tap an answer to check yourself. When you're ready, take the scored version in the free practice test.
These 10 free CDSP questions are organized by exam domain, so you can see how each part of the Certified Data Science Practitioner blueprint is tested. Reveal the answer and explanation under each question.
Domain 1: Defining the need to be addressed through the application of data science (7-9%)
Question 1
A retail company wants to predict subscription cancellations. Before selecting an algorithm, what should the data practitioner establish first?
Show answer & explanation
Correct answer: B - Business objective, success metrics, stakeholders, and constraints
Domain 2: Extracting, Transforming, and Loading Data (17-25%)
Question 2
A dataset contains duplicate records, missing values, and inconsistent formats. What is the appropriate first approach?
Show answer & explanation
Correct answer: B - Inspect, validate, clean, transform, and document the data
Question 3
A practitioner combines public demographic data with internal customer records. What should occur before use?
Show answer & explanation
Correct answer: A - Confirm permissions, privacy requirements, and data-use agreements
Question 4
Which technique converts text documents into numerical representations for machine learning?
Show answer & explanation
Correct answer: A - TF-IDF or Word2vec vectorization
Domain 3: Performing exploratory data analysis (25-36%)
Question 5
A dataset contains extreme income outliers. Which central tendency measure is least affected by them?
Show answer & explanation
Correct answer: B - Median
Question 6
A categorical region variable is converted into separate binary columns. Which method was used?
Show answer & explanation
Correct answer: B - One-hot encoding
Question 7
Two input variables contain nearly identical information. Which approach helps reduce redundancy?
Show answer & explanation
Correct answer: A - Feature selection or dimensionality reduction
Domain 4: Building models (19-27%)
Question 8
A model predicts whether a customer will default or not default on a loan. Which problem type is this?
Show answer & explanation
Correct answer: A - Classification
Question 9
A fraud model incorrectly flags legitimate transactions as fraudulent. Which metric is especially relevant?
Show answer & explanation
Correct answer: A - Precision
Question 10
A model performs well on training data but poorly on new data. What issue is most likely?