Descriptive analytics can tell you a lot about your business. It can help you identify your organisation's strengths and weaknesses, understand how your business has performed over time and show you how you compare with your competitors.
What is descriptive analytics?
Descriptive analytics is when you ask, 'What happened?' It's a type of data analytics in which you gather historical data to get a better idea of how your business has performed, progressed or changed.
You can analyse numerical data like annual turnover, or qualitative data like customer identifiers (e.g. gender, ethnicity, etc) or a combination of the two. You commonly present your results in easy-to-digest visuals like charts and graphs.
If you're new to data analytics, descriptive analytics is a good place to start as it's the simplest of the four main types of data analysis. Later in this guide, we'll look at the other three types in more detail.
Why is descriptive analytics useful in business?
Descriptive analytics is useful in business because it finds patterns and anomalies that help you better understand how your organisation is doing. You can use it to share these details with your stakeholders in a way that everyone can understand.
This keeps everyone on the same page and sets a solid foundation for other types of analytics. It can also help you with financial reporting and future planning.
How to implement descriptive analytics
To implement descriptive analytics, you need to know what data to gather, how to organise it and how to present it to your stakeholders. Here are the four key steps for carrying out descriptive analytics:
1. Identify metrics to track
Identifying which metrics to track is the first step. Do you want to look at quantitative or qualitative data? Do you want to measure sales, production or customer satisfaction? What timeframes will you be pulling the data from? Be clear about which metrics you're going to track before you move on to gathering the data.
2. Extract and compile data
Extract and compile data that'll report on the metrics you'll view. You might need to sift through external and internal sources like databases and CRMs to locate the data you want.
When compiling the data, you should choose a single format and stick to it. Consistency is key in making sure your data is well-organised. For numerical data, you might like to use a program like Excel. For qualitative data, Word might be more appropriate.
3. Perform data analysis
Perform data analysis by applying a mathematical operation to at least one variable. You can do this yourself — manually or using spreadsheet formulas — or you can use reporting software.
MYOB Business has financial reporting and analysis built into each plan, so you can get the insights you require at the click of a button.
4. Present data
Present data to colleagues and stakeholders using compelling visual forms like charts and graphs. These easy-to-understand formats make the information more accessible to everyone.
Real-world examples of descriptive analytics
Social media engagement metrics
Social media engagement metrics are important to track if you use social media to market your business. For example, go to the insights sections of your social media channels to see which posts are resonating most with your audience. Or look at your website analytics data to see which campaigns have driven more traffic to your site.
Ecommerce consumer trends
Ecommerce consumer trends are useful if you sell products through an online shop. Most ecommerce software providers offer easy-to-use reporting functionality, giving you quick access to your sales figures. These stats will tell you about the demand for each of your products, which can be used to help you plan future launches.
Financial statement analysis
Financial statement analysis is something you should do regularly to track your company's financial health. Documents like balance sheets, income statements and cash flow statements can help you identify growth or decline in your business, which will help you plan and prepare for the future.
Advantages of descriptive analytics
The advantages of descriptive analytics are so plentiful that it's the most popular of the four types of data analytics. But the key to its popularity lies in its simplicity. Data can be easily communicated to stakeholders and decision-makers by collating facts and figures into easy-to-digest visuals. Simplifying complex information improves people's understanding, keeping everyone up to date with your company's progress.
Descriptive analytics can also be used to compare yourself to your competition. The metrics used for descriptive analytics are largely universal, so it's easy to find data from other organisations to compare yourself against.
Disadvantages of descriptive analytics
The disadvantages of descriptive analytics are more complex than the advantages.
It's great for telling you what happened, but it can't tell you why it happened or what you could do in the future. If you're using analytics for planning purposes, you can't rely on descriptive analytics alone.
Another drawback: descriptive analytics relies on the quality of your data. Extracting data from limited sources, choosing the wrong metrics or excluding subsets of data can make your analysis misleading, biased or inaccurate. When performing descriptive analytics, you must be aware of your own biases and how these could affect your data collection.
Descriptive analytics vs alternative data analytics types
Descriptive analytics vs alternative data analytics types: how do you know which type is the one you need? As the simplest of the four types, descriptive analytics is a good introduction for analytical novices and can give you a solid foundation for further analysis. But if you want to look further than simply what happened, you'll need to consider one of these three alternative data analytics types:
Prescriptive analytics
Prescriptive analytics is the most advanced of the four types of data analytics. It looks at large amounts of data against a specific prediction and recommends the best course of action. An example of prescriptive analytics in action is fraud detection in banking. In this scenario, an algorithm analyses your spending history and contacts your bank in the event of anomalies with suggested actions to take.
Predictive analytics
Predictive analytics uses machine learning, AI and statistical modelling to find patterns in historical data and predict what might happen in the future. You might use predictive analytics for inventory forecasting or sales forecasts, to improve operational efficiency or for scheduling product launches.
Diagnostic analytics
Diagnostic analytics explains why certain events and behaviours happen. For example, if your descriptive analysis showed a sales revenue uptick for a certain product, you can use diagnostic analytics to investigate the cause.
Descriptive analytics FAQs
What is the relationship between descriptive and prescriptive analytics?
The relationship between descriptive and prescriptive analytics is about what you want to measure.
If descriptive analytics asks, 'What happened?', prescriptive analytics asks, 'What should we do next?' If you're new to data analysis, you'll want to start with descriptive analytics. It's easy to implement and great at simplifying complex business situations. However, it doesn’t consider what might happen in the future, and it doesn't give you any solutions or next-step recommendations.
Prescriptive analytics considers all your data and tells you what you should do next. It's a more advanced type of data analysis that can be expensive to implement and requires a lot of know-how, so it might not be right for your business just now. But if you're looking to automate business decisions and minimise risk caused by human error and bias, it's worth considering.
What are the risks associated with descriptive analytics?
The biggest risk associated with descriptive analytics is the human factor. Before running a data analysis, you and your stakeholders must agree on what metrics you'll be analysing. It's not uncommon for businesses to focus on favourable metrics and ignore others, leading to a skewed view of the organisation's performance.
It's also easy to make mistakes when collecting data. If the data you're analysing is low quality, your results will be unreliable and inaccurate.
Is descriptive analysis qualitative or quantitative?
Descriptive analysis can use both quantitative and qualitative data. Examples of quantitative data include revenue, profit and expenditure. Qualitative data, data that can't be measured or counted easily, could include customer descriptors like gender, ethnicity and location.
Harness the potential of data analytics
If you're looking to grow your business, you'll need to build data analytics into your processes. Descriptive analytics is the best place to start — it costs little to implement and requires hardly any analytical knowledge from you and your team.
MYOB makes data collection and descriptive analysis a piece of cake. With our accounting software, you can view your company's financial information and generate reports at the click of a button. Get started today.
Disclaimer: Information provided in this article is of a general nature and does not consider your personal situation. It does not constitute legal, financial, or other professional advice and should not be relied upon as a statement of law, policy or advice. You should consider whether this information is appropriate to your needs and, if necessary, seek independent advice. This information is only accurate at the time of publication. Although every effort has been made to verify the accuracy of the information contained on this webpage, MYOB disclaims, to the extent permitted by law, all liability for the information contained on this webpage or any loss or damage suffered by any person directly or indirectly through relying on this information.