A Guide to Effective Data Storytelling 📊
Unlock the art of data storytelling with key vocabulary
Hello, data-driven and curious minds, welcome to the 20th edition of DataPulse Weekly.
Imagine captivating an audience with numbers, transforming data into stories that drive action. In today's data-driven world, this essential skill is known as data storytelling.
While technical data analysis skills are important, what truly sets a great analyst apart is the ability to distill complex information into engaging, easy-to-understand narratives. Let’s dive into how to master this skill.
Consider these typical scenarios faced by businesses:
Why did the number of orders drop last week?
What caused the delivery time to increase by 10% yesterday?
Why did the engagement of a specific product feature decrease by 20% this month?
As analysts, we delve into data to uncover patterns and answers. For instance:
Orders dropped because our conversion rate declined.
Delivery time increased due to an out-of-stock situation.
Engagement decreased following an app update.
While these findings are valuable, presenting them in a story that resonates with our audience will set us apart as analysts.
Good data storytelling needs to answer these three questions:
1. What are the key elements of the data storytelling?
Data & Insights: Summarize key insights from the data concisely.
Visualization: Use charts or graphs to clearly illustrate the findings.
Context and Recommendations: Provide background, explain the significance, and offer actionable advice.
2. Who is the audience?
Identify the audience, such as CXOs, department heads, or specific roles, and understand their objectives.
3. How to craft the data storytelling?
Use the standard format of characters, setting, conflict, and resolution.
Now let’s implement this framework to our example of “Why did the number of orders drop last week?”
1. What are the key elements of data storytelling?
Data & Insights: The number of orders decreased due to a lower conversion rate of new users following an app update. Existing user's orders remain intact.
Visualization: A bar chart could show the drop in orders before and after the app update, and a line graph could depict the conversion rate over time across new and existing users.
Context and Recommendations: The app update caused an issue on the address page, leading to new users dropping off before completing their purchases. It is recommended to identify and resolve the address page issues and consider releasing a new update to prevent further sales loss while fixes are made.
2. Who is the audience?
Chief Business Officer: Expecting a high-level overview with a focus on business impact. Highlight how the drop in orders affects revenue forecast.
Head of Growth: Looking for insights on how the app update impacted user acquisition and engagement. Emphasize user behavior changes and suggest growth strategies to re-engage users.
Product Manager: Interested in detailed findings about the app update’s impact on user experience. Provide specific data on user feedback, conversion rates, and technical issues.
3. How to craft the data storytelling?
Characters: Internal & external players - The key players in this story are the new users who experienced the app update, the Chief Business Officer focused on revenue growth, the growth team responsible for user acquisition, and the product team that implemented the update. It’s important to know who your audience is when presenting your story.
Setting: Key problem - Show the conversion rate and orders of new vs. existing users across pre and post-app update periods in a graph. Highlight the decline in new user acquisition due to a lower conversion rate post-app update. For illustrative purposes, the graph below shows the conversion rate declining from 2.6% to 1.5% for new users.
Conflict: Root cause - The conversion rate dropped significantly due to an issue with adding an address during the checkout process after an app update. Show the drop by displaying the conversion rate for new users across older and newer app versions. For illustrative purposes, the latest version has 80% of new users with a conversion rate of 1.2%, whereas the older versions still have a conversion rate of 2.7%. Furthermore, we can solidify our claim by analyzing the conversion funnel from "add to cart" to "add an address" for new users across different app versions.
Resolution: Recommend the product team release a new app version to fix the address bug. Suggest the growth team send out notifications to affected users, encouraging them to update the app by highlighting the improved experience, to recover lost revenue. Update the Chief Business Officer (CBO) on the potential revenue impact to reassess targets.
Effective data storytelling requires precise vocabulary and clear concepts to convey your findings accurately and engagingly. Below are a few essential concepts to know:
Vocabulary and Concepts
Use the Right Data Vocabulary: Terms like probability, likelihood, chances, or possibility can help convey the nuances of your findings. For example, instead of saying "sales will increase," say "there's a high likelihood that sales will increase."
Avoid Absolutes: Provide context rather than raw numbers. Instead of "Our orders are 3,000," say "Our orders decreased by 40% compared to last month."
Clarify Percentages: Differentiate between percentage points and percentages. For example, a rise from 10% to 15% is a 5 percentage point increase but a 50% increase in percentage terms.
Compare Groups Effectively: Always present data from a period or group without the change for comparison. For example, if you implemented a new feature, compare user engagement before and after the feature's release.
Feasible Recommendations: Ensure your recommendations are practical and executable.
Be Open to Questions: Expect and appreciate contradictory opinions and questions—they can lead to deeper insights and better solutions.
Avoid Analysis Paralysis: In our opinion, distilling your story into three key points helps to keep our audience focused and avoid overwhelming them with too much information.
By optimizing these elements, we can transform data into compelling stories that not only inform but also drive action and decisions.
Conclusion
Mastering data storytelling transforms complex data & analysis into engaging narratives that drive actionable insights. By focusing on key findings, visualizations, and context, and tailoring the message to the audience, analysts can effectively communicate their analysis. Using the characters, setting, conflict, and resolution framework, we can craft compelling stories that inform and drive decisions, making data analysis more impactful and understandable. Additionally, using the right vocabulary ensures clarity and precision in conveying data insights.
That wraps up our newsletter for today! If you found this valuable, please consider subscribing and sharing it with a friend—it motivates us to create more content. Next time you are dealing with a data problem, remember the three key elements of data storytelling and how you can present your story using the characters, setting, conflict, and resolution framework.
Until next Tuesday!
Recommended Next Read:
Great insights and recommendations. In an age where pretty much half of an employee's career goes in understanding what level of complexity and detail should be presented at each level, this definitely gives a good starting point or checklist I'd say.
Beautifully explained 👌🏻👍🏻