For the majority of today’s organizations, data analytics is front and center. It plays a key role in driving business strategy, improving financial performance, and increasing efficiency, among its many other uses. According to a recent study by MicroStrategy, 94% of enterprises have confirmed that data analytics is important to business growth, while another 65% have planned to increase their analytics spending. 

The term “data analytics” is a catchall for the four main types of analytics: descriptive analytics, diagnostic analytics, predictive analytics, and prescriptive analytics. Each type has a specific objective that it seeks from the data, and most organizations use these types of analytics in tandem with one another in order to analyze their data from multiple angles. 

What is descriptive analytics? 

Descriptive analytics is arguably the most common type of analytics; it seeks to “describe” what is going on or what has happened thus far with the data by analyzing trends in current and historical data. In that sense, descriptive analytics helps the organization level set their understanding of the data. 

Descriptive analytics can involve many different complex data types. However, it is often regarded as the simplest form of analytics since its objective is to tell a fairly straightforward story, such as, “Our usage data grew 5% in 10 months” or “30% of our customer database resides in Europe.” Descriptive analytics doesn’t employ more advanced techniques that ask deeper questions of the data.

What are the pros and cons of descriptive analytics? 

Descriptive analytics answers some of the most important questions around business performance. It aligns closely with organizational goals and metrics, and is often used to indicate whether the organization is on track or falling short. Since every department in the organization must, in some way, measure their performance, every department uses some form of descriptive analytics.

That being said, descriptive analytics doesn’t seek to answer the “why,” the “what will be,” or the “what should be done” with regard to data trends—that falls into the realm of diagnostic analytics or predictive analytics. Descriptive analytics can’t, for example, explain why revenue has been decreasing, if it will continue to decrease, or what an organization should do to correct course—all very important questions. 

Descriptive analytics offers an important foundation for any additional analytics initiatives. However, it is best used when it is regarded as just that—a starting point. Most analytic initiatives will produce better results when descriptive analytics provide the landscape of the data, and further analytics are performed on top of that to best determine next steps and what should be done. 

What are common examples of descriptive analytics? 

Descriptive analytics initiatives vary widely. Here are a few examples of how descriptive analytics can make a big impact: 


Sales Channel Performance

Aggregate data from various sales channels to understand where your business is best performing. Is it through Amazon? Your eCommerce site? Your brick-and-mortar store? This descriptive analytics initiative should also be able to tell you how those trends have shifted through time. For example, perhaps Amazon spikes in sales around Black Friday, but the brick-and-mortar store gets more traffic in spring as the weather improves.

While this is a great start, it’s worth employing other types of analytics, such as diagnostic analytics (to understand why these trends are occurring), or predictive analytics (to understand how these trends may shift in the future).

Social Media Goals

This is perhaps the most straightforward example of descriptive analytics—organizations may set a specific goal (in this case, social media engagement) and track numbers such as follows, retweets, and engagements across different channels to determine their progress.This, again, is another great example of where additional analytics could be leveraged on top of this analysis to understand why one channel is increasing traffic at a faster rate, or how channels are expected to  perform in the future.

Customer Ticketing Trends

Descriptive analytics isn’t just about spotting trends over time, but relating those trends to other characteristics. For example, you might track customer help desk tickets and realize that a certain age demographic consistently has difficulty with a certain product feature. Or, that another age demographic responds more positively when emojis are used in the customer chat box. Descriptive analytics has the potential to connect the dots, explaining what relationships exist between data so that you can then ask deeper questions of it.

Personal Finance Analysis

Descriptive analytics isn’t just for organizations; analyzing our daily financial habits, for example, can make a big impact on our behavior. There are a variety of modern applications that do the work for you of analyzing every credit card purchase and grouping your spending habits into categories, offering a real-time, visual snapshot of where you could cut back. As your habits change over time, so does the data, offering you both a present and past analysis of your finances. 


What are the steps involved in descriptive analytics?

Descriptive analytics follows a similar process to most analytic initiatives—it starts with a clear goal in mind, requires identifying and preparing the right data, and concludes with a presentation of the data in a compelling, visual format. 


  1. Identify your goal.
    Analytics initiatives should have a goal to serve as a guidepost. Make sure your goal is closely aligned with the overarching goals of the organization and is actionable—that is, the results will provide a clear next step, whether that be conducting additional analysis or shifting business strategy.
  2. Locate the required data.
    Sourcing the right data is not always easy—data can be scattered across several different databases or applications. Make sure you plan ahead to understand what data you need, and how to best access it.
  3. Cleanse and prepare data.
    As the old adage goes, “garbage in, garbage out”—in other words, all data should be cleansed and prepared to ensure accurate and understandable final results. While not the most glamorous work, it is just as much a part of analytics as the end analysis itself, and deserves careful attention and thorough review.
  4. Analyze data.
    Organizations can use a variety of tools to analyze descriptive analytics initiatives. This includes spreadsheets, such as Excel, basic visualization tools, such as Google Charts, as well as more comprehensive business intelligence (BI) software, such as Tableau or Power BI. The complexity of the descriptive analytics initiative will help dictate which tool is required.
  5. Present data.
    Lastly, the results of the initiative must be presented in a clear, easy-to-understand format for business stakeholders. This may include a report, a data visualization, or a dashboard. Reports are best used for straightforward information, such as financial metrics, while data visualizations shine in their ability to visually represent trends and patterns. Finally, dashboards are best used if the initiative is ongoing, as in the case for sales revenue or social media engagement. 


What techniques are involved in descriptive analytics? 

Fundamental to the execution of a descriptive analytics initiative are several data engineering and analytics techniques, which include: 

  1. Data profiling: used to examine available data and discover the best datasets for the initiative. 
  2. Data pipeline building: used to ingest and deliver data from different sources to a downstream location or application. 
  3. Data preparation: used to prepare data for analysis, which may involve removing errors, replacing null values, standardizing values, joining columns, or enriching data with new information.
  4. Data validation: used to ensure the quality of the data being used. 
  5. Data visualization: used to visually present data in a compelling, easy-to-understand format that clearly communicates the results of the initiative.

Historically, the skills required for descriptive analytics have been beyond the technical realm of most business users. However, with the introduction of new, user-friendly tools, business users are now taking greater ownership over this work, as well as more efficiently collaborating with IT. These new user-friendly tools include software like Tableau, which allows users to build their own complex data visualizations, and Alteryx Designer Cloud, the self-service data engineering cloud platform.


How does a self-service data engineering platform power descriptive analytics? 

Designer Cloud’s self-service data engineering cloud platform provides a no-code/low-code environment that allows business users to utilize their data on their own or in collaboration with IT. Using Designer Cloud, business users performing descriptive analytics can easily source the data they need, prepare and transform their data as needed, ensure data quality, and deliver the end result to downstream analytics applications or dashboards. Instead of waiting for IT to deliver requirements, business users can use Designer Cloud to implement and execute new descriptive analytics initiatives faster than ever. 

Designer Cloud is unique because it is the only open and interactive cloud platform that allows this type of collaboration to occur between data engineers and business analysts. It has accelerated descriptive analytics (and many other analytic initiatives) for organizations big and small. 

Final thoughts 

Descriptive analytics is a mainstay in pretty much every organization (and even in our personal lives). It can summarize historical and current data trends, as well as point to relationships between data, all of which can play a huge role in tracking progress and driving business strategy. 

Descriptive analytics, however, is not the end-all-be-all, and many descriptive analytics initiatives would benefit from the use of further analytics. User-friendly tools have played a huge role in increasing the efficiency of descriptive analytics initiatives, and should be considered by any data-driven organization looking to increase or enhance data utilization. 

Start Wrangling

Kick off your 30 day free trial


Accelerate Data Engineering for the Cloud

Transform data, ensure quality, and automate data pipelines at any scale