To achieve the state of streaming insight offered by Big Data, we have to have a basic understanding of statistics. Don't worry, I'm not going to spend time on the math. Rather, we'll look at those factors that help your data scientist pick the right tools, based on the decisions you need to make and the data you have on hand, so that you can stream insight to those who need it most. First, though, there are different forms of analytics used in different ways. The most common are those analytics that form the basis of the reports you get or give, but there are also discovery analytics and production analytics.
Illustrated in Figure 6.1 is the cycle of analytics, from reporting to discovery to production. Reporting analytics are those statistics used to compare aspects of the business, such as salespeople or marketing campaigns. Discovery is the application of statistics to your data to understand why something is happening, while production analytics are those models that select offers (like Target's offers to expectant mothers) or make other decisions automatically.