The Art of Eight in Analytics


Analytics is not just about algorithms and numbers. Every analytics practitioner will tell you that there is an “art” to it – when to combine variables to extend data in the data warehouse, what options to set in the algorithm to get the best balance of accuracy and interpretability, how to define an outcome when it’s never been measured before. Although being “analytical” is a left brain concept, analytics practitioners regularly tap into the right brain for the creativity to answer these everyday questions.

But just as there is an art to doing analytics, there must be an art to explaining it, as well, particularly to those who do not have the same love of algorithms and numbers. This is Context, without which there is a disconnect between those that do the analytics and those that decide whether to action on the analytics.

Here are eight methods I’ve come across in my journeys as an analytics practitioner that anyone can mix and match to supplement the numbers.

1. Pictures
They really do tell a thousand words. If your audience is new to a concept, using a picture that can be understood without a lot of explanation (25 words or less as a guide) is an easy way to describe concepts. Google Images or your own photo albums are a great resource for this.

2. Videos
In this day and age of do more in less time, social media and easy-to-use recording software, the moving picture will always be effective in capturing the attention of an audience. Videos of less than a minute are great for demonstrating specific functionality. Longer videos can be used to tie into a story or limbic (see points 6 & 7). Have you seen the latest SAS YouTube videos?

3. Graphics
Graphics unlike pictures have standard formats e.g. arrows, processes, hierarchies. Whether using default graphics such as Smart Graphics in MS Powerpoint, Word Clouds or graphics found on the internet, the high-definition format of graphics and well defined colour palettes provide an eye-catching focus point that audiences can follow.

4. Visualisation
Tables and lists may be informative but they are rarely easy to interpret. Creating bar and line charts, plotting dimensions geospatially and using traffic lighting to differentiate severities will take less effort to explain and keep your audience’s attention longer. The interactive and attractive nature of SAS Visual Analytics is a great way of presenting complex analytical results.

5. Parameterised Reports
For presentations which need to be repeated regularly either as data is updated or for differently focused audiences, pre-defining levers which can be pulled in reports such as filters, hierarchy dimensions and cut-offs can save you a lot of time in recalculating metrics. The interactivity of parameterised reports also gives audiences more opportunity to be engaged in the presentation.

6. Stories
Why do we all remember the plot to Forrest Gump? Because it was a story most of us could relate to in some form, and though full of adventures, it had a simple “boy loves girl” plot. Using a story that your audience can identify with will clearly contextualise the analytics. For example, receiving an irrelevant offer from an organisation you have been a loyal customer for ten years, how you felt on the matter and your subsequent behaviour. If you want to tell a story visually on a single page, there is nothing better than an infographic. This visual combination of art and data can work in still or movement like in the AMEX ads on TV. Have a look at this previous SAS blog on how you can create infographics for your organisation.

The key to the success of any story though is that the storyteller (designer in the case of infographics) has a clear understanding of the objective. Without this, stories can turn out to be more confusing than informative for the audience.

7. Limbic or Themes

Having a theme run through the presentation lets an audience contextualise concepts and outcomes to the same subject. If this subject is relevant to the audience they will easily follow the presentation so either keep it specific to the interests of the stakeholder or generic to be safe. It’s important to note that themes do not work for all presentation audiences – particularly those that are only after the facts, so for these, stick with graphics, visualisation and parameterised reports.

8. Less is More
Keep the page “clean and simple”. Clean: don’t overload the screen with pictures and graphics or embed too many different attempts to explain a topic. Simple: don’t mix too many analogies lest you confuse the audience and use stories and themes that can be easily explained afterwards.

Just as the brain is made up of both left and right sides, Analytics and the ability to be creative in both its application and its presentation make up a complete equation. For an analytical viewpoint on different techniques to describe your data check out the Harvard Business Review whitepaper Visualizing Data.

These holidays, remember that Analytics can be fun… when treated with a little Art!

PS: Eight is made up of 2 zeros joined together, is an infinity when knocked sideways and is perfectly symmetric. What a beautiful number!


About Author

Business Solutions Manager

Annelies believes that there is potential for Analytics everywhere. She works as an evangelist, enabler and execution strategist to empower individuals and organizations with good Analytics practices. Annelies is the Advanced Analytics technology lead at SAS Australia and New Zealand responsible for product management and enablement. During her career, Annelies has held various positions supporting the customer lifecycle from strategy and requirements to implementation and adoption. This experience gives her a practical view of the end-to-end process of data analysis across government and industry, including engagements in several customer analytics, demand forecasting, text analysis and allocations optimization projects. Annelies is the current co-chair of the NSW Chapter of the Institute of Analytics Professionals of Australia, the largest analytics community in Australia. She has a research Masters in Mathematical Statistics and guest lectures at several tertiary institutes in Australia.

Comments are closed.

Back to Top