Big Data is not about the data. — Gary King
What exactly is “Big Data”? Big Data is data comprising four components, the 4 V’s: volume, variety, velocity and veracity, according to Robert Carraway, Darden School of Business. Carraway teaches Quantitative Analysis courses in Darden’s MBA program at UVA.
He says the first V, for volume, is indeed big. For statisticians of old, having a large volume of data was the ‘holy grail’. It enabled them to avoid the countless adjustments and disclaimers resulting from not having enough data.
The second V of big data is variety. Carraway says data is now collected and stored in many ways and in different locations. Each piece of data may contain a different piece of information about you.
The third V of big data is velocity. He says it’s data that is collect and is immediately accessible to whomever has access to it. Velocity enables you to react quickly enough to make a difference.
And finally, the fourth V of big data is veracity. Carraway says the problem with data is it may or may not be accurate. Either due to human or machine error. He says if the same information is being entered as data multiple times in multiple different ways, a collection of data from different sources could trigger to immediately question the veracity of a recent incorrect entry.
In summarizing the four V’s, Carraway says we may get suspicious about how big companies could use big data to manipulate us. But, he says, they can also use data to offer lower prices through improved productivity and not waste money on ineffective advertising, or make products with no demand. You can view his full comments here.