Data Science & Big Data Quiz

1. What are the '3 Vs' that define Big Data?

1. Value, Velocity, Variance
2. Value, Volume, Veracity
3. Volume, Validity, Velocity
4. Volume, Velocity, Variety

2. What is a 'data scientist' and what skills does the role typically require?

1. A database administrator who manages enterprise data systems
2. A professional who collects, cleans, analyses, and interprets large datasets, combining programming, statistics, and domain expertise
3. A scientist who studies climate data exclusively
4. An AI engineer who builds machine learning models only

3. What is 'machine learning' and how does it differ from traditional programming?

1. In traditional programming, humans write explicit rules; in machine learning, algorithms learn patterns from data to make predictions or decisions without being explicitly programmed
2. Machine learning is faster computing; traditional programming is slower
3. Machine learning only works for image recognition; traditional programming handles everything else
4. Machine learning uses quantum computers; traditional programming uses classical computers

4. What is a 'neural network' in machine learning?

1. A computational model loosely inspired by the human brain, using layers of interconnected nodes (neurons) to process and learn from data
2. A physical network of computing nodes
3. A system for connecting multiple computers for parallel processing
4. A type of database optimised for large datasets

5. What is 'overfitting' in machine learning?

1. When a model is too large to run on available hardware
2. When a model learns training data too precisely — memorising noise rather than patterns — and performs poorly on new data
3. When a model takes too long to train
4. When too much data is used for training, leaving insufficient data for testing

6. What is 'SQL' and why is it fundamental to data science?

1. Scalable Query Logic — a machine learning framework
2. Statistical Query Language — a statistical software package
3. Structured Query Language — used to query, manipulate, and manage relational databases
4. System Quality Language — a software testing standard

7. What is the purpose of 'data visualisation' in data science?

1. Converting data into a format computers can process
2. Creating beautiful graphics for marketing materials
3. Representing data graphically to communicate insights, reveal patterns, and enable understanding that would be difficult to extract from raw numbers
4. Storing large datasets more efficiently using visual compression

8. What is 'A/B testing' in data science and technology?

1. A controlled experiment comparing two versions (A and B) of something — like a webpage or feature — to determine which performs better statistically
2. A testing framework for software code quality
3. Comparing datasets from two different sources for accuracy
4. Testing two different machine learning algorithms against each other

9. What is 'Hadoop' and what problem did it solve in big data processing?

1. A cloud computing platform by Amazon
2. A database management system for structured data
3. A programming language for statistical analysis
4. An open-source framework for distributed storage and processing of very large datasets across clusters of commodity hardware

10. What does 'ETL' stand for in data engineering?

1. Encrypt, Transform, Load
2. Entities, Tables, Links — a database design methodology
3. Evaluate, Test, Launch
4. Extract, Transform, Load — the process of moving data from source systems to a data warehouse

11. What is the difference between 'supervised' and 'unsupervised' machine learning?

1. Supervised learning is more accurate; unsupervised learning is faster
2. Supervised learning requires a teacher; unsupervised learning is self-taught by the computer
3. Supervised learning runs on servers; unsupervised learning runs on edge devices
4. Supervised learning trains on labelled data (known inputs and outputs); unsupervised learning finds patterns in unlabelled data without predefined output labels

12. What is a 'data warehouse' and how does it differ from a regular database?

1. A backup storage system for important databases
2. A distributed database system spread across multiple servers
3. A physical building where computer servers are stored
4. A system optimised for analytical queries on large historical datasets — structured differently from OLTP databases designed for fast individual transactions

13. What is 'correlation' and why does the phrase 'correlation is not causation' matter in data science?

1. Correlation and causation are identical concepts — the distinction is a philosophical technicality
2. Correlation is a weak relationship; causation is a strong one
3. Correlation measures how similar two datasets look; causation means they were collected at the same time
4. Correlation measures statistical relationship between two variables; 'not causation' reminds us that a relationship doesn't prove one thing causes the other

14. What is 'Python' and why is it the dominant language in data science?

1. A database query language for analytical workloads
2. A general-purpose, high-level programming language favoured in data science for its readable syntax, vast library ecosystem (NumPy, Pandas, scikit-learn, TensorFlow), and active community
3. A scripting language used only for web automation
4. A statistical computing language developed specifically for data analysis

15. What is 'natural language processing' (NLP) and what are its common applications?

1. A compression algorithm for storing text data efficiently
2. A protocol for natural language communication between APIs
3. AI techniques enabling computers to understand, interpret, and generate human language — used in chatbots, sentiment analysis, translation, and voice assistants
4. Software that translates programming languages between each other

16. What is the 'bias-variance tradeoff' in machine learning?

1. A fundamental tension where reducing model error from bias (oversimplification) increases variance (sensitivity to noise) and vice versa — finding the optimal balance is central to model selection
2. Balancing the trade between biased training data and variable outputs
3. Choosing between biased algorithms and unbiased algorithms
4. The tradeoff between model accuracy and computational cost

17. What is 'GDPR' and how has it affected data science practices?

1. General Data Protection Regulation — EU law requiring explicit consent for data collection, right to erasure, and data minimisation — reshaping how companies collect and use personal data
2. Global Data Privacy Rules — an international treaty on data security
3. Google Data Processing Regulations — Google's internal data policies
4. Government Data Protection Requirements — US federal data privacy law

18. What is 'feature engineering' in machine learning?

1. Designing the physical hardware features of ML computing systems
2. Documenting the features and capabilities of a trained model
3. The process of selecting which machine learning model to use
4. The process of using domain knowledge to create or transform input variables (features) that make ML models more effective

19. What is 'Apache Spark' and how does it improve on Hadoop MapReduce?

1. A cloud-specific data processing framework
2. A competitor to Python's Pandas library for data manipulation
3. A streaming database for real-time analytics
4. A unified analytics engine for big data processing that processes data in-memory rather than writing to disk — making it 10–100x faster than Hadoop MapReduce for many workloads

20. What is a 'confusion matrix' in machine learning evaluation?

1. A matrix showing how confusing training data was to process
2. A method for comparing multiple model architectures simultaneously
3. A table summarising classification model performance — showing true positives, false positives, true negatives, and false negatives
4. A visualisation of how different features are correlated