With data science and machine learning having gone mainstream, there is a ballooning of interest and expectations. However, many of these expectations do not match reality.
Data viz is seen to be a mysterious field best left to experts or large enterprises with deep pockets. It also many a times misunderstood as something unessential to the “core” task of data analysis.
At KnowledgeHut, some of our data science experts busted three common myths that drive data viz folks crazy. Here’s their take.
Data viz can be used to produce beautiful and elaborate diagrams. There are several examples of data patterns displayed as a tapestry for art. While this may serve as an instrument to draw users’ attention to key features, there is much more to data viz as a whole.
Data viz draws from varied fields like graphic design, statistics, human-computer interaction, and data management. Acquiring, parsing, and refining the data are parts of the process.
As one of our data science experts shared, there have been several times where his team spotted data flaws in the data visualization process which saved his company from making huge mistakes.
To break down the steps in creating a data viz, let’s start with the business setting. You need to first identify the target audience, the problem at hand, and the corporate goals. To get to this, you need to get to the heart of the end-users’ true goals - for instance, is the goal to figure out why there was a drop in sales or to figure out why this drop happened. You then need to figure out how best to answer business questions with data, including what to do about missing or unclear data and doing checks to ensure the right info is conveyed with the data viz.
With data viz, much of the cognitive heavy-lifting is already taken care of. However, there is still a tendency to misinterpret results that are easier to understand. These tend to be perceived as being easy to produce, which brings us to the next myth.
While tools like Tableau and Datawrapper, along with programming packages like ggplot2 and seaborn, data can be visualized in a few lines of code or even just a number of clicks. This makes the last mile of the data viz process easy and simple.
However, there’s a ton of work that goes into this. Although several calibrations go into this largely iterative process, the last part of creating data viz tends to be most overstated as described in this HBR article by Scott Berinato.
Good design isn’t just about coming up with an aesthetic look. And while styling is part of the design, it’s not at all the most important part.
Additionally, data viz practitioners need to ensure that they don’t unintentionally obscure, distort, or misrepresent with their visual models. These steps may be hidden from the user perspective but are just as crucial.
The wrong visualization method can create a misleading chart as shown in this article by the Economist on post-Brexit referendum attitudes. The original chart gave a false impression representing a rather erratic view.
It exasperates data viz practitioners when people think all that all they do is to tinker with aesthetics. In actuality, they spend much of their time researching books and articles, analysing the data, and expending much energy considering and eliminating possible design options before arriving at the final data viz product. The discarded drafts are not seen by the end-user.
The challenge is further compounded when shifting from developing one-off data viz pieces to a reproducible system.
Given the growth of interactive data tools and advanced visualizations, there is a perception that data viz is hard to access or is the result of elaborate and expensive processes.
However, data viz is just about contextualizing data for people’s consumption. Anyone interested in communicating data effectively—be it someone from a grassroots organization or a school student—can benefit from data viz practices.
The right working process and understanding of dataviz methodology and concepts, can elevate the most basic examples of data viz. The skill to remove visual details that distract instead of inform, orto use colour cues to emphasizing trends, even in something as familiar as a table of figures, allows one to craft a more compelling message. No fancy software is required. It can even be done on the back of a napkin.
While best practices in data visualisation are evolving fast, what may be acceptable today may be frowned upon tomorrow. New and better techniques are emerging all the time and it is imperative to stay on top of things. As the data viz community expands, it is important that misconceptions that stand in the way of the field’s maturation and professionalization are cleared.
Yes, data visualization has gone mainstream. Now let’s leverage its impact.
Your email address will not be published. Required fields are marked *