WGU C207 DATA-DRIVEN DECISION MAKING EXAM GUIDE
2026/2027 | Verified Answers 100% Correct | Complete Study
Resource | Pass Guaranteed - A+ Graded
Section 1: Foundations of Data-Driven Decision-Making & Analytics
Maturity
Q1: A retail company makes inventory decisions based on the CEO's "gut feeling" from
20 years of experience rather than sales data analysis. This represents:
A. Data-driven decision making with predictive analytics
B. Evidence-based management with diagnostic analytics
C. Intuition-based decision making without data support [CORRECT]
D. Prescriptive analytics with optimization modeling
Correct Answer: C
Rationale: Intuition-based decision making relies on experience, instinct, and personal
judgment rather than data analysis. While experience has value, this approach misses
opportunities for optimization and may perpetuate biases. Data-driven decision making
(A, B, D) explicitly uses data, statistical analysis, and analytical models to inform
choices.
Q2: According to Davenport's analytics maturity model, which stage involves using data
to understand why something happened?
A. Descriptive analytics answering "what happened"
B. Diagnostic analytics answering "why did it happen" [CORRECT]
C. Predictive analytics answering "what will happen"
D. Prescriptive analytics answering "what should we do"
Correct Answer: B
,Rationale: Davenport's four stages of analytics maturity progress from descriptive (what
happened) to diagnostic (why did it happen—root cause analysis, drill-down,
correlations), to predictive (what will happen—forecasting, modeling), to prescriptive
(what should we do—optimization, simulation). Diagnostic analytics bridges
understanding past performance and predicting future outcomes.
Q3: A hospital analyzes patient readmission rates by department and time period to
identify patterns. This is an example of:
A. Prescriptive analytics recommending specific interventions
B. Predictive analytics forecasting future readmissions
C. Descriptive analytics summarizing historical data [CORRECT]
D. Cognitive analytics using artificial intelligence
Correct Answer: C
Rationale: Descriptive analytics summarizes historical data to understand what
happened—using basic statistics, dashboards, and reports. This hospital is analyzing
past readmission rates, not predicting future events (B) or recommending actions (A).
Cognitive analytics (D) involves AI and natural language processing, not basic historical
analysis.
Q4: Which characteristic of big data refers to the speed at which data is generated and
must be processed?
A. Volume referring to massive data quantities
B. Velocity referring to data generation and processing speed [CORRECT]
C. Variety referring to different data types and sources
D. Veracity referring to data quality and uncertainty
Correct Answer: B
Rationale: The 5 V's of big data: Volume (amount), Velocity (speed of
generation/processing), Variety (structured/unstructured types), Veracity
(quality/accuracy), and Value (usefulness). Velocity is critical for real-time applications
,like fraud detection, algorithmic trading, and IoT sensor monitoring where delays reduce
value.
Q5: A dataset contains customer names, purchase dates, and satisfaction ratings from
1-5 stars. The satisfaction ratings represent which measurement scale?
A. Nominal scale with categorical labels only
B. Ordinal scale with ordered categories [CORRECT]
C. Interval scale with equal intervals and no true zero
D. Ratio scale with equal intervals and true zero
Correct Answer: B
Rationale: Ordinal scales have ordered/ranked categories where differences between
values aren't necessarily equal. Star ratings (1-5) are ordered (5 > 4 > 3) but the
difference between 1-2 stars may not equal 4-5 stars in customer perception. Nominal
(A) has no order. Interval (C) has equal intervals. Ratio (D) has a true zero point (ratios
meaningful—10 kg is twice 5 kg).
Q6: A manufacturing company collects sensor data from machinery every millisecond
to detect anomalies in real-time. This data source is best classified as:
A. Internal structured data from transactional systems
B. External secondary data from industry reports
C. Internal unstructured data from IoT sensors
D. Internal structured data with high velocity [CORRECT]
Correct Answer: D
Rationale: Machine sensor data is internal (generated by the company), structured
(timestamp, sensor ID, measurement value), and high velocity (millisecond frequency).
While IoT sensors (C) are involved, the data is typically structured, not unstructured.
External data (B) comes from outside sources. Transactional systems (A) typically
involve business events, not continuous sensor streams.
, Q7: Which analytics type would recommend the optimal price for a product considering
demand elasticity, competitor pricing, and inventory levels?
A. Descriptive analytics showing historical pricing trends
B. Diagnostic analytics explaining past price changes
C. Predictive analytics forecasting demand at various prices
D. Prescriptive analytics determining optimal pricing strategy [CORRECT]
Correct Answer: D
Rationale: Prescriptive analytics goes beyond prediction to recommend specific actions
that optimize outcomes. It uses optimization algorithms, simulation, and decision
analysis to determine the best course of action given constraints and objectives. Price
optimization considering multiple factors and recommending a specific price is classic
prescriptive analytics.
Q8: A data lake differs from a data warehouse primarily in that a data lake:
A. Stores only structured, processed data for specific purposes
B. Stores raw data in native format before structuring [CORRECT]
C. Requires data to be cleaned before storage
D. Is designed only for batch processing, not real-time
Correct Answer: B
Rationale: Data lakes store raw, unprocessed data in native formats (structured,
semi-structured, unstructured) without predefined schemas—"schema on read" rather
than "schema on write." Data warehouses (A, C) store processed, structured data with
predefined schemas for specific analytical purposes. Both can support batch and
real-time processing (D).
Q9: AutoML (Automated Machine Learning) represents which advancement in analytics
for 2026?
A. Manual feature engineering by data scientists
B. Automated model selection, hyperparameter tuning, and deployment [CORRECT]
C. Elimination of all human oversight in model development
D. Restriction of analytics to simple descriptive statistics only
2026/2027 | Verified Answers 100% Correct | Complete Study
Resource | Pass Guaranteed - A+ Graded
Section 1: Foundations of Data-Driven Decision-Making & Analytics
Maturity
Q1: A retail company makes inventory decisions based on the CEO's "gut feeling" from
20 years of experience rather than sales data analysis. This represents:
A. Data-driven decision making with predictive analytics
B. Evidence-based management with diagnostic analytics
C. Intuition-based decision making without data support [CORRECT]
D. Prescriptive analytics with optimization modeling
Correct Answer: C
Rationale: Intuition-based decision making relies on experience, instinct, and personal
judgment rather than data analysis. While experience has value, this approach misses
opportunities for optimization and may perpetuate biases. Data-driven decision making
(A, B, D) explicitly uses data, statistical analysis, and analytical models to inform
choices.
Q2: According to Davenport's analytics maturity model, which stage involves using data
to understand why something happened?
A. Descriptive analytics answering "what happened"
B. Diagnostic analytics answering "why did it happen" [CORRECT]
C. Predictive analytics answering "what will happen"
D. Prescriptive analytics answering "what should we do"
Correct Answer: B
,Rationale: Davenport's four stages of analytics maturity progress from descriptive (what
happened) to diagnostic (why did it happen—root cause analysis, drill-down,
correlations), to predictive (what will happen—forecasting, modeling), to prescriptive
(what should we do—optimization, simulation). Diagnostic analytics bridges
understanding past performance and predicting future outcomes.
Q3: A hospital analyzes patient readmission rates by department and time period to
identify patterns. This is an example of:
A. Prescriptive analytics recommending specific interventions
B. Predictive analytics forecasting future readmissions
C. Descriptive analytics summarizing historical data [CORRECT]
D. Cognitive analytics using artificial intelligence
Correct Answer: C
Rationale: Descriptive analytics summarizes historical data to understand what
happened—using basic statistics, dashboards, and reports. This hospital is analyzing
past readmission rates, not predicting future events (B) or recommending actions (A).
Cognitive analytics (D) involves AI and natural language processing, not basic historical
analysis.
Q4: Which characteristic of big data refers to the speed at which data is generated and
must be processed?
A. Volume referring to massive data quantities
B. Velocity referring to data generation and processing speed [CORRECT]
C. Variety referring to different data types and sources
D. Veracity referring to data quality and uncertainty
Correct Answer: B
Rationale: The 5 V's of big data: Volume (amount), Velocity (speed of
generation/processing), Variety (structured/unstructured types), Veracity
(quality/accuracy), and Value (usefulness). Velocity is critical for real-time applications
,like fraud detection, algorithmic trading, and IoT sensor monitoring where delays reduce
value.
Q5: A dataset contains customer names, purchase dates, and satisfaction ratings from
1-5 stars. The satisfaction ratings represent which measurement scale?
A. Nominal scale with categorical labels only
B. Ordinal scale with ordered categories [CORRECT]
C. Interval scale with equal intervals and no true zero
D. Ratio scale with equal intervals and true zero
Correct Answer: B
Rationale: Ordinal scales have ordered/ranked categories where differences between
values aren't necessarily equal. Star ratings (1-5) are ordered (5 > 4 > 3) but the
difference between 1-2 stars may not equal 4-5 stars in customer perception. Nominal
(A) has no order. Interval (C) has equal intervals. Ratio (D) has a true zero point (ratios
meaningful—10 kg is twice 5 kg).
Q6: A manufacturing company collects sensor data from machinery every millisecond
to detect anomalies in real-time. This data source is best classified as:
A. Internal structured data from transactional systems
B. External secondary data from industry reports
C. Internal unstructured data from IoT sensors
D. Internal structured data with high velocity [CORRECT]
Correct Answer: D
Rationale: Machine sensor data is internal (generated by the company), structured
(timestamp, sensor ID, measurement value), and high velocity (millisecond frequency).
While IoT sensors (C) are involved, the data is typically structured, not unstructured.
External data (B) comes from outside sources. Transactional systems (A) typically
involve business events, not continuous sensor streams.
, Q7: Which analytics type would recommend the optimal price for a product considering
demand elasticity, competitor pricing, and inventory levels?
A. Descriptive analytics showing historical pricing trends
B. Diagnostic analytics explaining past price changes
C. Predictive analytics forecasting demand at various prices
D. Prescriptive analytics determining optimal pricing strategy [CORRECT]
Correct Answer: D
Rationale: Prescriptive analytics goes beyond prediction to recommend specific actions
that optimize outcomes. It uses optimization algorithms, simulation, and decision
analysis to determine the best course of action given constraints and objectives. Price
optimization considering multiple factors and recommending a specific price is classic
prescriptive analytics.
Q8: A data lake differs from a data warehouse primarily in that a data lake:
A. Stores only structured, processed data for specific purposes
B. Stores raw data in native format before structuring [CORRECT]
C. Requires data to be cleaned before storage
D. Is designed only for batch processing, not real-time
Correct Answer: B
Rationale: Data lakes store raw, unprocessed data in native formats (structured,
semi-structured, unstructured) without predefined schemas—"schema on read" rather
than "schema on write." Data warehouses (A, C) store processed, structured data with
predefined schemas for specific analytical purposes. Both can support batch and
real-time processing (D).
Q9: AutoML (Automated Machine Learning) represents which advancement in analytics
for 2026?
A. Manual feature engineering by data scientists
B. Automated model selection, hyperparameter tuning, and deployment [CORRECT]
C. Elimination of all human oversight in model development
D. Restriction of analytics to simple descriptive statistics only
