The Evolution of Data-Driven Decisions: Descriptive Analytics

By: Katana Graph

March 14, 2022

The Evolution of Data-Driven Decisions: Descriptive Analytics

The term “analytics” encompasses an entire realm of thought about processing data. There are several different kinds of analytics, but all of them strive to gain some sort of understanding from data. Modern analytical methods tend to be lumped into four groups: descriptive, diagnostic, predictive, and prescriptive.

As with many other scientific fields, most of which have their own evolution of analytics, business analytics began as descriptive, simply chronicling events that had happened. Descriptive analytics answer “what happened?” They help businesses generate narratives, supported by charts and tables, to further market products or development as a company. This type of analytics helps uncover the reasoning behind prior successes or failures and can be used to prevent future failures or encourage future successes.

For example, as late as the mid-1800s, several European countries were offering state-owned insurance with no concept of actuarial science; policies were priced similarly for an 80-year-old as they were for a 10-year-old. When they eventually collected statistics seeking descriptive data about individuals, they came to realize that patterns appeared, describing subpopulations or reference classes. They then realized that they could use this descriptive data to predict the overall tendencies of a group of people. These days we likewise separate the population into reference classes, a discretized population, to make more personally relevant, individualistic predictions.

Zooming out to businesses in general, the types of descriptive analytics traditionally applied include simple numerical values such as returns on invested capital (ROIC, a single scalar value derived from net income, dividends, and total capital), net profit margin, and customer acquisition cost. Seasonal traffic analysis, website traffic, and lead conversion statistics are types of descriptive analytics that involve multidimensional data and more complex data views.

As we move toward more precise, focused data we keep statistics on keystrokes, user clicks, and time spent on a given webpage. With this data, businesses can track consumer trends and use it to take steps towards goals like more relevant advertising. However, descriptive analytics alone rarely produces meaningful insights. Descriptive analytics are used to determine what events have taken place within a reference class, but if we want to understand why these events have taken place, we must shift over to diagnostic analytics. We’ll do so in a subsequent post.

Whether structured or unstructured data, Katana Graph can greatly improve the insights and opportunities uncovered from your organization’s data. Click to schedule a meeting.

share

Newsletter Sign Up

Optimizing Large-Scale Distributed Graph Neural Networks on Intel CPUs

Training Graph Neural Networks on Large Graphs Graph neural networks (GNNs) are a powerful tool for.

Read More
Rethinking Buyer Behavior Algorithms

To standard traffic analyzers, one click is as good as another. Our impulse purchases and our most.

Read More
Katana Graph’s Analytics Python Library

As businesses grow and face increasing data challenges, they must find ways to tackle more.

Read More

View All Resources

Let’s Talk

Turn Your Unmanageable
Data Into Answers

Find out how Katana Graph can help provide the foundation for your future of data-driven innovation.

Contact Sales