Machine learning model training
What is Behavioral Analytics?
What is Diagnostic Analytics?
The Difference Between Data Analytics and Statistics
Data Analytics vs. Business Analytics
What is Data Analytics?
The Difference Between Data Analytics and Data Visualization
Data Analytics vs. Data Science
Quantitative vs. Qualitative Data
Data Analytics Processes
Data Analytics vs. Data Analysis
Data Analytics Lifecycle
Data Analytics vs Business Intelligence
What is Descriptive Analytics?
What Is Google Analytics 4 and Why Should You Migrate?
Google Analytics 4 and eCommerce Tracking
GA4 Migration Guide
Understanding Data Streams in Google Analytics 4
GA4 vs. Universal Analytics
Understanding Google Analytics 4 Organization Hierarchy
Benefits and Limitations of Google Analytics 4 (GA4)
What are the New Features of Google Analytics 4 (GA4)?
What Is Customer Data?
Collecting Customer Data
Types of Customer Data
The Importance of First-Party Customer Data After iOS Updates
CDPs vs. DMPs
What is an Identity Graph?
Customer Data Analytics
Customer Data Management
A complete guide to first-party customer data
What Is a Customer Data Platform?
Customer Data Protection
Difference Between Big Data and Data Warehouses
Data Warehouses versus Data Lakes
A top-level guide to data lakes
Data Warehouses versus Data Marts
Best Practices for Accessing Your Data Warehouse
What are the Benefits of a Data Warehouse?
Data Warehouse Architecture
What Is a Data Warehouse?
How to Move Data in Data Warehouses
Data Warehouse Best Practices — preparing your data for peak performance
Key Concepts of a Data Warehouse
Data Warehouses versus Databases: What’s the Difference?
Redshift vs Snowflake vs BigQuery: Choosing a Warehouse
How to Create and Use Business Intelligence with a Data Warehouse
How do Data Warehouses Enhance Data Mining?
Data Security Strategies
How To Handle Your Company’s Sensitive Data
How to Manage Data Retention
Data Access Control
Data Security Technologies
What is Persistent Data?
Data Sharing and Third Parties
What is Consent Management?
What is PII Masking and How Can You Use It?
Data Protection Security Controls
Data Security Best Practices For Companies
We'll send you updates from the blog and monthly release notes.
What is Descriptive Analytics?
Descriptive analytics means analyzing data to answer questions of the form “what happened?” or “what is happening?” Answering questions of the form “what happened?” is more specifically known as historical (or static) analytics, whereas answering questions of the form ‘‘what is happening?” is known as real-time analytics. Descriptive analytics can be used either on its own to answer simple business questions like “Did overall sales go up or down last month?” or alongside other, more complex forms of data analytics to reach specific company goals.
This page explains what descriptive analysis is, describes how you can use descriptive analytics to inform strategic business decisions and organizational choices, provides examples of descriptive analytics in practice, and discusses its benefits and limitations.
Descriptive analytics definition
Descriptive analytics involves interpreting historical or real-time data to better understand trends or relationships between online customer-driven events. An event is an action taken by your customer online where they interact with one of your products or services, and these events can be recorded for the purpose of analytics. Descriptive analytics can help your company understand its market better, or to work out whether the business is on track to achieve its goals. It is the most basic form of data analytics in that it aims to answer simple, purely descriptive questions. Importantly, descriptive analytics does not aim to answer “why” something happened.
As such, descriptive analytics is often an organization’s entrypoint into the data analytics space. It is common to begin with descriptive analytics and then, with more experience, move on to more complex types of data analytics such as predictive analytics, customer data integration or the 360-degree customer view.
This type of analytics doesn’t attempt to predict the future (predictive analytics), give reasons why something happened (diagnostic analytics), or what action should be taken (prescriptive analytics). However, descriptive analytics is an essential part of data analytics, as a solid understanding of the past can provide useful insights. Its limitation is that it only answers basic questions; however, it can be paired with other types of data analytics methods to give a more rounded view of a business.
How does descriptive analytics work?
First, your company must decide on a question that can be answered using descriptive analytics. This means it must be about an event or trend that happened in the past or is currently happening. It is common for companies to use key performance indicators (KPIs) to guide their questions, as these are their most important company goals. The people who want to know the answers to the questions will be your project stakeholders. Once your stakeholders know what questions they want to ask, you must ensure that you have access to the data you need to answer them. If you don’t, you need to find a way to collect this data before you can begin your descriptive analytics work.
Next, aggregate all the data that may be relevant to answering your particular question together in one place. Using data purchased from third parties (alongside your own first-party data) can be helpful, as it can provide you with more information to answer your question. Aggregating your data into one place may involve an ETL (extract, transform, load) process: extracting data from various different locations, transforming it so that all the relevant data goes into a single table, view, or dataframe for ease of querying, and then loading it into a new location (usually inside a data warehouse).
Now that your data is aggregated together, you can do some exploratory data analysis. This involves investigating your data set to look for any useful information or anomalies, which may give insights that will help when cleaning your data later. For example, if you find that a disproportionately high percentage of people have input "Mr." for their title, you may need to investigate, as this is often the default value for a title field. You could compare their first names to a list of names that have a definite gender attached to them, enabling you to fix some of these values (you won’t be able to fix all the values, as some names are gender-neutral).
Exploratory data analysis can also help you decide on the most appropriate model for your main analysis work. This could be a SQL model, or a statistical model such as linear regression or a clustering algorithm. However, for descriptive statistics, by far the most common model to use is a SQL model, as SQL lends itself very well to performing groupings and aggregates like sums, counts, averages, and percentiles. Combining that with SQL being far easier to learn than complex statistics or machine learning, you can see why descriptive analytics and SQL often go hand in hand.
Once you’ve decided on your model type, it’s time to build it. If you’ve chosen a SQL model, this is best built by a data analyst. If it’s a statistical model, you’ll need to use your judgment of your and your team’s skill sets to decide if a data analyst or a data scientist is best placed to do this work. Either way, you will need an experienced and knowledgeable person to choose a suitable statistical model from the many that exist.
The final stage is to produce the requested outcome to your stakeholders in the form of a report or data visualization. It’s a great idea to make use of charts or other visualizations to form a data narrative – storytelling is a great way to ensure that your stakeholders are engaged and that they understand the importance of your analysis. Remember that some charts are more appropriate than others for certain types of data, and you should familiarize yourself with the best data visualization techniques for different types of data analytics questions.
Depending on the scope of your research, and your organization’s budget, a descriptive analytics project can consist of answering a single question, where the project ends once the requested answer has been communicated to stakeholders. Alternatively, your descriptive analytics project can serve as a jumping-off point for more complex projects such as prescriptive analytics.
Benefits of descriptive analytics
Using descriptive analytics allows teams to understand what happened within your company, which then enables them to change what they are doing if their KPIs are not being met. Descriptive analytics is easier to implement than other types of analytics, and allows you to quickly spot trends and patterns, or to detect problems. You can then use this information to help decide how your business proceeds with its product, service, or marketing strategy to improve profit and efficiency.
The information that descriptive analytics provides can often be used to make small but efficient changes to your business workflow. Automated alerts can be set up based on the outcome of your descriptive analytics — for example, an unexpected decrease in week-over-week web traffic or conversions could automatically trigger an email alert.
Descriptive analytics typically uses simple reporting measures and analysis techniques, including line, bar, and pie charts, which a wider business audience can easily understand. It can also be used together with other data analytics techniques (diagnostic, predictive, and prescriptive analytics) to provide a more comprehensive picture of your business.
Examples of descriptive analytics
Descriptive analytics provides tangible benefits to your company by asking well-formulated questions that have a clear, achievable answer, such as “How many users did our website have last month?” or “What was the conversion rate for our most recent marketing campaign?” Some examples of how descriptive analytics can be used across different sectors of a business are explained below.
You can use descriptive analytics to produce financial reports on month-over-month sales growth or year-over-year product price changes. These reports allow you to monitor your company’s financial health over time.
Social media engagement
Your marketing team can use descriptive analytics to help them find out what content is most popular, and they can use this data to work out what kind of content they should share in the future. They could start by generating reports on how their social media likes, shares, and clicks change each month.
Web traffic reports
If your web team wants to improve your company’s website, a web traffic report is an example of descriptive analytics that can show the popularity of different pages on the site (by seeing how many users are clicking on each page). The team can then analyze their successful web pages to work out what they are doing right.
Descriptive analytics can be used to identify trends in customer preferences and behavior regarding your product. You can use this to make a reasonable guess about future demand for particular features of your product. Netflix, for example, uses descriptive analytics to power the “trending now” part of its recommendation system. The popularity of this system is evidenced by the fact that 80% of all content streamed on Netflix comes via its recommendation system.
General business reports
You can use descriptive analytics to generate internal business reports on metrics like stock or cash flow to get a snapshot of how your company is operating. Creating these reports can help you work out ways to improve efficiency, such as a new strategy for restocking products.
Your company can use descriptive analytics reports as the basis of automated alerts; for example, when web traffic or key events decline by more than a specified amount, an automated email alert could be sent to the appropriate member of staff, enabling them to catch issues as early as possible.
Descriptive analytics and customer data platforms
Descriptive analytics deals with historical data and involves detecting patterns and trends to better understand your business. When used alongside diagnostic, predictive, and prescriptive analytics, the information from descriptive analytics allows you to make even more informed decisions on your marketing strategies and other business functions.
Customer data platforms can help save time collecting this historical event data in the first place, or at the ETL stage during descriptive analytics projects. Instead of data analysts having to extract data from various sources, transform the data, and load it into a data warehouse, a customer data platform can automate much of this process. It allows you to set up a data pipeline between your different data sources and your data warehouse, continuously transforming your data into a useful format as it is loaded into the data warehouse. This allows data analysts to focus on the other steps in the descriptive analytics process.