Practice C14-001–012
Record answer / confidence 1–5 / time / deciding clue before opening diagnostics.
C14-001 — Foundations & Analytics · Foundational · Recall
Which statement best distinguishes Big Data from Data Science in Chapter 14? - A. Big Data describes the management challenge/environment of large, fast, varied data; Data Science describes the analytical/scientific practice used to derive insight and models. - B. Big Data means any data set above 100 TB; Data Science means any analysis below that threshold. - C. Big Data is unstructured data only; Data Science is structured data only. - D. Big Data is historical reporting; Data Science is only real-time automation.
C14-002 — Foundations & Analytics · Foundational · Recall
A dashboard explains what happened last quarter and why. Which analytics category best fits? - A. Predictive analytics. - B. Descriptive analytics / traditional BI. - C. Prescriptive analytics. - D. Reinforcement learning.
C14-003 — Foundations & Analytics · Standard · Distinguish
A model assigns each customer a 0-100 probability of churn next month. What is the best classification? - A. Descriptive analytics. - B. Prescriptive analytics. - C. Predictive analytics. - D. Operational analytics.
C14-004 — Foundations & Analytics · Standard · Apply
A churn system not only predicts risk but recommends the retention offer most likely to prevent the customer from leaving. Which classification is strongest? - A. Descriptive analytics. - B. Predictive analytics only. - C. Data profiling. - D. Prescriptive analytics.
C14-005 — Foundations & Analytics · Standard · Understand
Why does Chapter 14 describe Data Science as iterative? - A. Results can refine requirements, expose new hypotheses, require new data sources, and change the model before or after deployment. - B. Because every model must use all available data sources before it can be evaluated. - C. Because Data Science replaces business requirements with algorithmic discovery. - D. Because models should be redeployed after every data record arrives.
C14-006 — Foundations & Analytics · Difficult · Understand
A team finds a technically impressive pattern in a huge data set, but no business decision or measurable benefit can be tied to it. What is the best Chapter 14 response? - A. Deploy it because large data sets are likely to reveal future value. - B. Return to the business need/value gate before productionizing the finding. - C. Move immediately to the speed layer so the insight becomes real-time. - D. Increase the training-set size until a business use appears.
C14-007 — Big Data Characteristics & Architecture · Foundational · Understand
Which Big Data V refers to how difficult data is to use or integrate? - A. Velocity. - B. Volatility. - C. Viscosity. - D. Veracity.
C14-008 — Big Data Characteristics & Architecture · Standard · Distinguish
A supplier feed changes every few minutes and loses business value after one hour. Which V is the most direct clue about how long the data remains useful? - A. Velocity. - B. Volume. - C. Variety. - D. Volatility.
C14-009 — Big Data Characteristics & Architecture · Standard · Distinguish
Which statement correctly contrasts ETL and ELT in Chapter 14? - A. ETL transforms/integrates before loading; ELT loads/ingests first and transforms/integrates later for use. - B. ETL is for structured data and ELT is only for unstructured data. - C. ETL means no Metadata is needed; ELT requires Metadata. - D. ETL is real-time and ELT is batch only.
C14-010 — Big Data Characteristics & Architecture · Difficult · Apply
A data lake contains thousands of raw files. Every file has reliable source, lineage, structure, quality indicators, ownership, and searchable catalog Metadata. Analysts can find and understand the data. Which conclusion is best? - A. It is necessarily a data swamp because raw data has not been transformed. - B. It is a managed data lake, not a data swamp merely because the data is raw. - C. It must be converted to a relational warehouse before it can be governed. - D. It is a speed layer because the data is stored before transformation.
C14-011 — Big Data Characteristics & Architecture · Difficult · Apply
An analytic service needs complete historical results plus events from the last few seconds. Which architecture pattern best matches the chapter? - A. Use only the speed layer because real-time data is always more valuable. - B. Use only the batch layer because historical completeness should always dominate latency. - C. Use a batch layer for complete history, a speed layer for current data, and a serving layer to expose the combined view. - D. Use a data swamp so all records remain untransformed.
C14-012 — Big Data Characteristics & Architecture · Expert · Apply
A vendor proposes sub-second streaming analytics, but the business can take action only once per day and the low-latency design is much more expensive. What is the best response? - A. Choose the speed layer because Big Data should be real-time whenever possible. - B. Choose the most expensive architecture because it preserves future flexibility. - C. Skip model monitoring so the added latency cost is offset elsewhere. - D. Reassess the latency requirement and choose an architecture aligned to actionable business timing and cost/benefit.