Data visualization is often the final hurdle between turning data into insights and ensuring that insights from data are understood by the key people so they can make better-informed decisions and take the appropriate actions.
Countless hours of data exploration and analysis can go to waste if you fall at the last obstacle, by failing to communicate your findings effectively.
Unfortunately, data visualization mistakes are very common. Finding the best ways to visualize the data is often considered as an afterthought rather than a critical piece of the process. Poor data visualisations can lead to muddled messages and ultimately, poorly-executed and ineffective decisions.
So here are five key mistakes I see day in and day out. Avoiding these will ensure that your data analysis and reporting efforts will have the desired impact.
1. Starting without a clear strategy
As with every aspect of your analytics, having a clear strategy and goal in mind is essential when it comes to planning how you will use visualizations.
With a visualization, the goal will generally be to impart the wisdom gained through data wrangling and exploration to the right people, who are in the right place, at the right time – to use it and make a difference.
This strategizing should take place right at the start, as the first step of putting together a plan for data-driven transformation. Just as you are clear what the goals of your data gathering and analysis are (what do you want to find out?) you start thinking about the formats and methods that will be most effective to present it, visually.
2. Your data visualization doesn’t tell a clear story
Data storytelling is an essential part of getting your message and meaning across. Like all stories, a data story will have a beginning, a middle and an end. And also like a lot of stories, they won’t necessarily come in that order!
In fact, as a rule, with a data story, it’s often best – essential even – to start at the end. That’s because unlike a movie or novel story, we aren’t worried about giving away the ending. A data-driven story (particularly a business one) should be told more like a newspaper story – shouting your key findings in a headline at the top, and then backing it up with evidence as the reader gets drawn in.
As with a novel, movie or newspaper story, if you don’t build structure around the way it is told, then your audience will come away confused, unsure what (if anything) they are supposed to think, and possibly even with “wrong” ideas based on misinterpretation of your story.
Whatever direction you take your storytelling in, it’s essential to building a solid narrative that you keep intuitive – related facts should follow each other and draw your audience along the paths between evidence and conclusions.
3. Your data visualization tells too many stories
It can be very easy to overdo the amount of information you can cram into your graphs, infographics or dashboards. It’s important to identify the key messages in a data set and present them in a way that isn’t cluttered by extraneous and unnecessary detail.
While audiences can be motivated to keep track of complex and intertwined plotlines in TV shows like Game of Thrones, when it comes to presenting business data it’s far better to stick to a smaller number of crucial plotlines. It’s at this point in the process when an ability to be ruthless is a useful trait. If any data point, observation or statement doesn’t work towards developing the core narrative of your presentation – cut it.
Overly busy graphics and visualizations tire the eye and the brain – and they don’t stick in the mind nearly as well as those which make a simple and concise point, backed up with relevant and up-to-date facts and stats.
4. Not fitting your visualization to your audience
Data often tells different stories to different audiences. Part of the skill of building a narrative with data is understanding how it will be used and interpreted by different audiences. While a detailed breakdown of different machinery and their optimum operating conditions will be valuable to an engineer, an executive needs a more concise but broader overview of the situation. Not if and when an individual machine might break down, but rather how the company’s machines are working as a whole, and if they are helping or hindering the company when it comes to hitting its goals.
In either case, the information each member of the organization needs is likely to be contained within the same dataset, but needs to be presented differently to meet the needs of each audience.
5. Not grounding your data in the real world
Usually, the story your data should be telling, is what the abstract graphs and statistics mean in the real world. This means your data must be grounded by its real-life impact – what difference will the data make to the lives of your customers, your team, or whichever humans you are presenting it to?
It’s all very well knowing that a certain re-arrangement of a window display or the wording of a personalized customer relations email will increase visitor numbers at your place of business by a certain amount. But what is the bottom line impact? How will this really help you achieve your goals or drive positive and sustainable change?
If employees have targets to meet, and the point of a data-driven initiative is to increase the frequency with which those targets are hit, then your visualizations should include the real-world implications of this. This could be happier customers, lower rates of customer cancellation or return or progress towards incentives such as bonuses. If your visualization is designed to show executives the opportunities which can be realized by taking the business along diverging paths, it should clearly show the impact on metrics such as profits, turnover and staff retention.
Avoiding these data visualization mistakes will be a big step towards the more effective use of data, clearer insights and ultimately better data-driven decision-making leading to improved business performance.
Bernard Marr shares five common mistakes that can be easily avoided for better data analysis: