WGU C207 DATA-DRIVEN DECISION MAKING EXAM
2026/2027 | Actual Questions and Answers | Latest Updated
Graded A+ | MBA Analytics Prep | Pass Guaranteed
Competency 1: Data Analytics Lifecycle (10 Questions)
Q1
A healthcare system's Chief Analytics Officer is initiating a new project to reduce patient
readmission rates. The team has completed defining the business problem and is now
identifying data sources including EHR records, claims data, and patient satisfaction
surveys. Which phase of the data analytics lifecycle is the team currently executing?
A. Data preparation
B. Data exploration
C. Business case evaluation and data understanding [CORRECT]
D. Model deployment
Correct Answer: C
Rationale: The data analytics lifecycle (CRISP-DM framework adapted for business)
begins with business understanding (problem definition) followed by data
understanding (identifying sources, assessing quality, and initial data collection). The
scenario describes the transition between these phases—problem defined, now
sourcing data. Option A (Data preparation) involves cleaning and transforming data, not
yet begun. Option B (Data exploration) involves profiling and visualization, which comes
after data acquisition. Option D (Model deployment) is the final operational phase.
,Q2
A retail company has deployed a customer churn prediction model. After three months,
the analytics team discovers the model's accuracy has degraded significantly because
customer purchasing behavior shifted due to a new competitor entering the market.
Which lifecycle management activity is required?
A. Model retraining with updated data and potential feature engineering [CORRECT]
B. Returning to the initial business problem definition phase
C. Abandoning predictive analytics for descriptive reporting only
D. Increasing the model's complexity without data updates
Correct Answer: A
Rationale: Model drift (concept drift) occurs when the relationship between inputs and
outputs changes over time, degrading predictive performance. The appropriate
response is model maintenance through retraining with recent data and potential
feature adjustments. Option B is excessive; the business problem remains valid. Option
C abandons valuable predictive capability. Option D compounds the problem by adding
complexity to outdated relationships.
Q3
During the data preparation phase, a data scientist discovers that 15% of customer
records have missing values for income level. Which approach represents best practice
for handling this missing data?
A. Automatically delete all records with missing income values
,B. Impute missing values using mean/median income or predictive imputation after
analyzing the missing data mechanism [CORRECT]
C. Replace all missing values with zero
D. Ignore the missing data and proceed with model building
Correct Answer: B
Rationale: Best practice requires analyzing the missing data mechanism (MCAR, MAR,
or MNAR) before selecting an approach. Imputation (mean, median, regression, or
multiple imputation) preserves sample size and reduces bias when appropriately
applied. Option A reduces statistical power and may introduce bias if data is not MCAR.
Option C distorts the distribution. Option D leads to biased or unstable models.
Q4
A manufacturing firm is transitioning from descriptive analytics to predictive
maintenance. Which sequence correctly represents the analytics maturity progression?
A. Descriptive → Diagnostic → Predictive → Prescriptive [CORRECT]
B. Predictive → Descriptive → Diagnostic → Prescriptive
C. Descriptive → Predictive → Diagnostic → Prescriptive
D. Prescriptive → Predictive → Diagnostic → Descriptive
Correct Answer: A
Rationale: The analytics maturity model progresses from: (1) Descriptive (what
happened?), (2) Diagnostic (why did it happen?), (3) Predictive (what will happen?), to
(4) Prescriptive (what should we do?). This represents increasing analytical
, sophistication and business value. Options B, C, and D present illogical sequences that
do not reflect organizational learning or capability building.
Q5
In the data exploration phase, an analyst generates summary statistics and
visualizations to understand variable distributions and identify outliers. Which statistical
measure is most appropriate for identifying the central tendency of a skewed salary
distribution?
A. Mean
B. Median [CORRECT]
C. Mode
D. Range
Correct Answer: B
Rationale: The median is robust to outliers and skewed distributions, making it the
preferred measure of central tendency for income data which typically follows a
right-skewed distribution. The mean (Option A) is pulled toward extreme values. The
mode (Option C) may not exist or be meaningful for continuous data. The range (Option
D) measures dispersion, not central tendency.
Q6
A project team has completed model building and is preparing to operationalize the
solution. Which activity is essential during the deployment phase?
A. Retraining the model on training data only
2026/2027 | Actual Questions and Answers | Latest Updated
Graded A+ | MBA Analytics Prep | Pass Guaranteed
Competency 1: Data Analytics Lifecycle (10 Questions)
Q1
A healthcare system's Chief Analytics Officer is initiating a new project to reduce patient
readmission rates. The team has completed defining the business problem and is now
identifying data sources including EHR records, claims data, and patient satisfaction
surveys. Which phase of the data analytics lifecycle is the team currently executing?
A. Data preparation
B. Data exploration
C. Business case evaluation and data understanding [CORRECT]
D. Model deployment
Correct Answer: C
Rationale: The data analytics lifecycle (CRISP-DM framework adapted for business)
begins with business understanding (problem definition) followed by data
understanding (identifying sources, assessing quality, and initial data collection). The
scenario describes the transition between these phases—problem defined, now
sourcing data. Option A (Data preparation) involves cleaning and transforming data, not
yet begun. Option B (Data exploration) involves profiling and visualization, which comes
after data acquisition. Option D (Model deployment) is the final operational phase.
,Q2
A retail company has deployed a customer churn prediction model. After three months,
the analytics team discovers the model's accuracy has degraded significantly because
customer purchasing behavior shifted due to a new competitor entering the market.
Which lifecycle management activity is required?
A. Model retraining with updated data and potential feature engineering [CORRECT]
B. Returning to the initial business problem definition phase
C. Abandoning predictive analytics for descriptive reporting only
D. Increasing the model's complexity without data updates
Correct Answer: A
Rationale: Model drift (concept drift) occurs when the relationship between inputs and
outputs changes over time, degrading predictive performance. The appropriate
response is model maintenance through retraining with recent data and potential
feature adjustments. Option B is excessive; the business problem remains valid. Option
C abandons valuable predictive capability. Option D compounds the problem by adding
complexity to outdated relationships.
Q3
During the data preparation phase, a data scientist discovers that 15% of customer
records have missing values for income level. Which approach represents best practice
for handling this missing data?
A. Automatically delete all records with missing income values
,B. Impute missing values using mean/median income or predictive imputation after
analyzing the missing data mechanism [CORRECT]
C. Replace all missing values with zero
D. Ignore the missing data and proceed with model building
Correct Answer: B
Rationale: Best practice requires analyzing the missing data mechanism (MCAR, MAR,
or MNAR) before selecting an approach. Imputation (mean, median, regression, or
multiple imputation) preserves sample size and reduces bias when appropriately
applied. Option A reduces statistical power and may introduce bias if data is not MCAR.
Option C distorts the distribution. Option D leads to biased or unstable models.
Q4
A manufacturing firm is transitioning from descriptive analytics to predictive
maintenance. Which sequence correctly represents the analytics maturity progression?
A. Descriptive → Diagnostic → Predictive → Prescriptive [CORRECT]
B. Predictive → Descriptive → Diagnostic → Prescriptive
C. Descriptive → Predictive → Diagnostic → Prescriptive
D. Prescriptive → Predictive → Diagnostic → Descriptive
Correct Answer: A
Rationale: The analytics maturity model progresses from: (1) Descriptive (what
happened?), (2) Diagnostic (why did it happen?), (3) Predictive (what will happen?), to
(4) Prescriptive (what should we do?). This represents increasing analytical
, sophistication and business value. Options B, C, and D present illogical sequences that
do not reflect organizational learning or capability building.
Q5
In the data exploration phase, an analyst generates summary statistics and
visualizations to understand variable distributions and identify outliers. Which statistical
measure is most appropriate for identifying the central tendency of a skewed salary
distribution?
A. Mean
B. Median [CORRECT]
C. Mode
D. Range
Correct Answer: B
Rationale: The median is robust to outliers and skewed distributions, making it the
preferred measure of central tendency for income data which typically follows a
right-skewed distribution. The mean (Option A) is pulled toward extreme values. The
mode (Option C) may not exist or be meaningful for continuous data. The range (Option
D) measures dispersion, not central tendency.
Q6
A project team has completed model building and is preparing to operationalize the
solution. Which activity is essential during the deployment phase?
A. Retraining the model on training data only
