Join Alan Simon for an in-depth discussion in this video Exploring the analytics taxonomy, part of Foundations of Business Analytics: Prescriptive Analytics.
- We tend to use the term analytics in an all-encompassing manner but in reality we have a number of different flavors of analytics to work with and each of these has its own specific purpose. All of these flavors should actually come together though to provide the broadest and deepest possible data-driven insights that we're after. Our simplest form of analytics and one that we've actually been working with for a number of years under different labels is called descriptive analytics. Then we have predictive analytics, discovery analytics, and then the subject of this course, prescriptive analytics.
Let's take a look at what each of these types of analytics do for us. A relatively straightforward taxonomy for these different flavors of analytics can help us see how they relate to one another. You can think of each of these types of analytics in the context of the types of questions you would ask and then the types of answers you would get to those questions. When we look at our simplest form, descriptive analytics, these are the types of questions along the lines of tell me what happened and why it happened as well as tell me what's happening right now and then why. Predictive analytics ask questions such as tell me what is likely to happen and why.
They look into the future whereas descriptive analytics typically look into the past or the present. When we come to discovery analytics, these are questions along the lines of looking for something interesting and important within all of our data even without asking very specific questions. So in other words we tend to be mining through our data and looking for interesting patterns and correlations and we'll talk more about those later. Finally prescriptive analytics, the subject of this course, guides us in telling us not only what is going on or what might have happened or what is likely to happen but what we should do about it and other things related to specific business actions we should be taking.
It's important to know where in this analytics continuum prescriptive analytics fit because it's more than just another flavor or variety. You can think of prescriptive analytics as the culmination or maybe even the final frontier of analytics. In general we acquire and organize our data and then we perform our first three types of analytics upon that data. We'll perform descriptive analytics to determine what has happened in the past or what might be happening right now. And we also do predictive and discovery analytics for their purposes.
Then we take the outputs of all three of these categories of analytics and we feed them into our prescriptive analytics engines and this is where we're guided on not only what is going on and all the insights that we're after, but what we should do about them. The important point to remember though is that this entire analytics continuum is essential to us. All four of these categories need to work together for us to give us the greatest business benefit that we're after.
- Exploring the analytics taxonomy
- Understanding prescriptive analytics fundamentals and workflow
- Looking at data warehousing and business intelligence
- Exploring big data
- Collecting and processing data
- Exploring triggering events
- Formulating business hypotheses
- Refining and enriching business hypotheses
- Reaching definitive conclusions
- Putting the finishing touches on prescriptive analytics