This site uses cookies and by using the site you are consenting to this. We utilize cookies to optimize our brand’s web presence and website experience. To learn more about cookies, click here to read our privacy statement.

Introduction to Data Science: Math + Tech = Business Smarts

In the data world, the terms gigabytes and terabytes seem incompetent. Companies need colossal-size storage – Brontobyte, anyone? It sounds like something out of a prehistoric world. But brontobytes are just one piece of a new technology buzzword – Data Science.

Today, industries are combining technology and advanced analytics to make more intelligent decisions. This is known as data science. People in this field – data scientists – use scientific approaches and mathematics to ask smarter questions. This helps them build a hypothesis and pass curated decisions back to the business.

At the same time, data science isn’t only about programming and math. The field also relies on thinking interest, pattern discovery, and innovation. Data scientists uncover new observations by creating and combing through attributes from different types of information. In addition, they find different avenues for future research. Therefore, a successful data scientists thinks critically, knows coding, and intelligently uses statistics.

Let’s start by looking at the basic evolution of the advanced analytics field.

Per Gartner there are four different levels of analytics based on its capability:

Gartner - Four Types of Advanced Analytics Capability in Data Science

Descriptive analytics

This is the initial, ground zero stage for data science. Descriptive analytics tells you “what happened”. It summarizes the history of data, which helps with future decision making. It also prepares data for further analysis. Most businesses have this capability either through a reporting solution (SQL Server Reporting Services, etc.) or, at the least, using Microsoft Excel with pivot charts and pivot tables.

Diagnostic analytics

At this stage, data scientists look a little deeper at data. This form of advanced analytics examines data to answer “Why did it happen?”. Diagnostic analytics reveals the causes of events and behaviors, using data drill down, mining, and correlation.

Predictive analytics

Predictive analytics is somewhat more complex. Here, data scientists use deep data mining to predict future probabilities and trends. They look for a prediction variable measured for an individual or multiple entities (features). This helps to predict future behavior.

Prescriptive analytics

The final, most ideal phase is prescriptive analytics. At this point, scientists not only understand and anticipate the “what” and “when” of something happening, they also foresee the “why.” An example is self-driving cars, which will one day talk to each other, self-learn, and make smarter decisions on the road.

According to a 2013 Gartner publication, prescriptive analytics falls into the “Innovation Trigger” time section, taking about 5 to 10 years to execute full force.

Hype Cycle for Emerging Technologies, 2013, in Data Science


In my next article, we’ll learn how SQL Server 2016 is a game changer.