The Four Vs of Big Data

Q1. What are the four Vs of big data?

A. Vulnerability, Variation, Velocity, Variety

B. Volume, Speed, Processing, Variations

C. Variations, Variable, Volume, Virtual

D. Volume, Veracity, Velocity, Variety

Q2. What does the speed of big data refer to?

A. Virtual

B. Veracity

C. Velocity

D. Variations

Q3. What does the amount of big data refer to?

A. Virtual

B. Vulnerability

C. Velocity

D. Volume

Q4. What does the different kinds of data refer to?

A. Variety

B. Veracity

C. Variable

D. Variable

Q5. What does the imprecise and incompleteness of big data refer to?

A. Vulnerability

B. Veracity

C. Variable

D. Volume

Q6. Which TWO of the following data sources are most likely to have veracity issues?

A. GPS location information from phones

B. An isolated internal management system

C. A temperature sensor

D. Self-reported data from online questionnaires

Rare events in random data

Q7. Consider a facial recognition system that is used in an airport. This system has cameras that collect images of people's faces and analyzes them against a database of known criminals. How reliable does the facial recognition system have to be such that on average it does not observe more than 20 false positives within a sample of 10 million people processed? Calculate the reliability as a percentage value. Write your answer to 5 decimal places (e.g. 12.12345). (Hint: reliability = 1- false positive rate )

Q8. Is the following statement True or False? A large expected number of events in random data usually makes mining for these events meaningless as a lot of false positives are generated. ( )

Q9. You are running an experiment where you roll a die six times. You are looking at the probability of rolling 6 sixes in one experiment out of k experiments. Let k=500, what is the probability that at least one of the k experiments shows 6 sixes? Write your answer as a proportion to 4 decimal places (e.g. 0.1234). ( )

Hint: The probability of rolling 6 sixs in one experiment if you roll a die six times is (1/6)^6 .

Q10. You are running an experiment where you flip a coin five times. You are looking at the probability of getting 5 heads in one experiment out of k experiments. Let k=20, what is the probability that at least one of the k experiments shows 5 heads? Write your answer as a proportion to 4 decimal places (e.g. 0.1234). ( )

Hint: The probability of getting 5 heads in one experiment of flipping a coin 5 times is 0.5^5