June 12, 2012
This is part of a series of posts from Typekit’s resident data analyst, Mike Sall. In this installment, Mike shares best practices for designing data.
A central part of analyzing data is thinking about how we need to look at the numbers to understand them. Data visualization is powerful because it can condense a lot of complicated information into a small space and so answer important questions. But this can only happen when the design allows those answers to show through.
The variety of charts out there may seem endless, but they really boil down to six core visual elements: grouping, size, position, angle, color, and annotation. When we visualize data, these elements are our building blocks. In this post, I’ll step through each of these visual elements and show how we can use them to design thoughtful visualizations of our data.
The most basic element we have in data visualization is grouping: how we aggregate all the underlying data into individual data points. This might sound obvious because we often go through this process without thinking about it. If we want to show quarterly revenues, for example, then clearly our data points are the revenue totals for each quarter. But why not monthly, or weekly, or daily, or even hourly?
Let’s say we’re charting user sign-ups and need to decide between daily and weekly granularity. If we’re trying to see whether we’ve improved over the last few months, then the fact that sign-ups naturally dip every weekend doesn’t matter; in this case, a weekly rather than daily grouping will help us more easily compare one week to the next and observe the overall trend. But if we announced a major feature on Tuesday and want to see how that affected sign-ups, then a weekly grouping isn’t going to help. We need to see sign-ups by day or perhaps even by hour to understand what effect the announcement had.
At the most basic level, the data points are the things we can distinguish in a chart, so they should represent the differences that actually interest us. By reducing them to the minimal granularity we need, we can ensure the design will focus on the differences we care about while filtering out the ones we don’t.
Once we have the specific data points we want to show, the next visual element we can use is size. Size simply refers to the amount of space a data point takes up. For example, to represent larger values, we can make the bars taller in a bar chart or the bubbles bigger in a bubble chart. When we make these distinctions, what we’re really doing is increasing the amount of visual mass a data point has, giving it more pixels or ink.
The visual element of size excels at representing quantities of stuff: people, dollars, orders, clicks, tweets, and so on. This compares with metrics that aren’t quantities, such as inflation rates, miles-per-hour, clickthrough percents, and other rates and calculated values; often, position is better for these kinds of values. But for quantities, we usually want to compare how much more or less stuff each point represents, and size shows these proportions.
To correctly see the differences, though, we have to be careful to maintain true proportions. If we were to change the y-axis of a bar chart so the bottom of every bar began at 100 instead of 0, then suddenly we’d be interfering with the proportion: a bar taking up twice as much space would no longer represent twice as much stuff. Similarly, if we’re using circles to represent size, we can’t just double the width to represent double the value since that would actually quadruple the circle’s area. Instead, we have to make sure the relative sizes of the data points preserve the true proportions of the values they represent. Only then can we accurately compare them.
At this point, we have determined which data points we want to show and how big or small they need to be. The next step is to decide where they go. This is our third visual element — position — and we can use it in different ways. In a bar chart, we can put the bars in chronological order to represent time. Or, in a scatter plot, we can place the dots at certain horizontal and vertical distances from the axes. By putting data points in specific places, the distance between them is what matters: if two data points are near each other, we know they are similar in some way, such as occurring at around the same time or representing comparable values.
Whereas size helps us observe proportions, position helps us observe proximities. We can easily see clusters of data points, or find the ones that sit closest to the axis, or spot the outliers. Because position helps us understand these relationships, it works best for representing distances, time, and calculations such as percentages and rate-per values. With more abstract or sequential values like these, position makes it easier for us to quickly see the landscape of values and relate the data points to each other.
Of course, sometimes the lines are blurry. Let’s say we wanted to compare a bunch of prices. Technically, we could think of that as a quantity: the quantity of dollars spent on each product. But we could also think of prices as a rate-per value: the price per product. Both size and position seem applicable here. To help us choose, we should consider our goals for the analysis. If we’re trying to understand how much more expensive certain products are than others — that is, to examine those proportions — then using size probably makes the most sense. But if we want to quickly point out which products are the most expensive or see which ones have the most similar prices, than position will help us better see those relationships. When there doesn’t seem to be an obvious answer, we should always refer back to the analytical questions we’re asking.
So now we have our separate data points of specific sizes, and we’ve decided where to put them. The next thing we can do is connect them — literally, draw lines from one to the next. Like grouping, this is something we often do without thinking about it. A line chart, for example, is simply connecting the dots of a scatterplot, and an area chart is connecting the bars of a bar graph.
When we connect data points like this, we’re not actually showing more information about the data points themselves but rather revealing the changes between them. We’re producing an angle. Angles are the fourth visual element at our disposal, and we can use them to see shifts and trends. But while they help show how something changes, they can also hide the individual values, making it more difficult to see where one point ends and another begins. So they come with a sacrifice: we should only use angles when we care more about overall trends than specific values.
A good example of this is stock price. When we plot a stock’s price over time, we often connect the dots to show a line graph. That’s because we care more about a stock’s return — how much the price has risen or fallen over time — than its specific price at any given moment.
Sometimes, though, it’s more difficult to decide whether or not angles are appropriate. For example, if we are graphing temperature over time, our visualization might differ depending on our objectives. If we wanted to examine global warming, then we would care more about the overall trend, so we would connect the data points to produce angles. But if we wanted to see what the average temperature was each month over the past year, then angles wouldn’t make sense: in this case, we care more about examining the individual values. As with the question of using size versus position, we have to think carefully about whether angles are useful for the questions we’re asking. Just because we can make an angle doesn’t mean we should.
After we’ve determined size, position, and angle, we have one more visual element we can use to represent data: color. Common uses of color include the blue versus red regions of an election results map or the separately colored categories of a stacked area chart. The nice thing about color is that, unlike size and position, we don’t have to make any extra room in the chart to accommodate different values. It’s an easy way to provide additional information without moving the data points around.
At the same time, though, we are limited by how well we can perceive differences. It’s difficult for us to interpret numeric figures from color — when we see a darker blue, we don’t think, “Oh, that’s about 20% darker.” Plus, we should always be cognizant of potential color blindness; the whole point of data visualization is, after all, to make information more universally readable.
Given these limitations, color works best as a tool for simplification, to help group data points into categories or gradations. When we see data points of the same color, we visually merge them together, allowing us to see broader differences. A choropleth map, for example, uses different colors and shades to represent different values on a map, helping us visually group geographic areas. In the below chart of US unemployment rates by county, the use of color groups granular data points into larger regions that are easier to digest, such as the lighter area in the Midwest.
But we walk a fine line when we use color, and we should always be aware of the limitations. When we use color to represent gradation, such as in the choropleth map, we do so at the expense of interpreting specific values. So, while color is helpful, we need to use it sparingly — only a few colors at once, and as a grouping mechanism rather than a way to indicate specific values.
Lastly, any information on a chart that is not itself data is annotation. Annotation is what helps us understand the data, and it can mean anything that serves this purpose: axes, grid lines, labels, titles, even comment blurbs that help point out specific things.
Generally, we want to keep annotation to a minimum. The point of a visualization is the data, and we should provide only as much annotation as necessary to understand it. If we have vertical grid lines for each week, can we do monthly instead? Or yearly? Or, for that matter, do we really need the grid lines at all? Perhaps just a couple value labels along the axis can do the trick. Or, to really simplify, maybe the whole point of the visualization is to show what happened on a particular date, so the only annotation we need is a single label.
Or maybe we really do need all those grid lines. This isn’t to say that the standard titles, labels, and grid lines we’re used to seeing are bad. Often they are necessary — they have become standard for a reason. We just need to be deliberate about the decisions we’re making, to make sure we’re using annotation on purpose rather than by default. Because ultimately, the less annotation we have, the more we can focus on the data itself.
Putting it all together
Of course, the most frustrating phrase that can come at the end of all this is: it depends. And it does. The rules aren’t airtight. Sometimes we should use size instead of position, sometimes not. Sometimes we need an angle, sometimes we don’t.
But the key is that it always depends on the questions we’re asking. That’s why we can’t just run some calculations and plop the results into the first chart we find. When we’re crafting a chart, we’re also examining what the numbers mean. These guidelines give us a place to start, but we must always remember that we visualize data to answer questions. Keep those questions in mind and the design will follow.
February 9, 2012
This is the second in a series of posts from Typekit’s resident data analyst, Mike Sall. Read the first.
One of the trickiest questions we can ask of data is how to compare a bunch of smaller items all at once. It’s also one of the most common questions, whether we want to analyze online advertisements, or understand different products, or compare customer segments by region. And to find an answer, we usually end up doing the same thing every time: we’ll take that list of items and rank them by some important value. For example, which online advertisements have the highest click rate? Or which products are purchased the most often? Or what are the top regions by revenue?
It’s an easy way to quickly see what’s important, which is why we do it. But rankings also obscure all the details that can help us figure out what to actually do about those important items. If we know which products are purchased most often, how can we tell whether it’s due to pricing, or features, or marketing? What we really need is to be able to discover trends — not just single numbers — that in turn reveal how we should act upon them.
In our last post on data we discussed one technique for analyzing trends, by visualizing one metric across other dimensions, such as the cancellation rate across time and period of use. This is great when examining the customer base as a whole or considering just a few segments, but it starts to break down when we try to compare dozens or even hundreds of segments at the same time; many graphs all together can be as opaque as the original data. So we need a new technique when we want to explore many segments at once.
To explain our approach, let’s use an example applicable to anyone with a website: traffic sources. We care about traffic sources because if we can better understand who’s sending us new users, we can better serve those users. Most tools like Google Analytics offer lots of data about traffic sources. For each source we can consider a range of metrics, from the number of visitors, to how long they spend on the site, how many of them sign up, and more.
To get to the trends we care about, though, we need to take a step back. First, we should focus our attention on the single most important metric; then, to find the trends, we can take that metric and break it apart — that is, we can look at its components. While the overall metric can help us understand which items are most important, its components will tell us why they are important.
For many online businesses like us, that key metric for web traffic is straightforward enough: revenue. Of course all of the other metrics around engagement are important too, but ultimately we hope traffic will drive people to sign up and purchase a plan.
With this metric in hand, we can now break it apart. To do that, let’s walk through the thought process for visitors purchasing a plan. First, they’ll decide to visit our site. Then, after browsing around, they’ll determine we fit their needs and decide to sign up for a plan. And lastly, they’ll look at the plans we offer and decide which plan they want. So, to understand how traffic sources are driving revenue, we can think about this metric in terms of the sub-decisions that comprise it: visits from the traffic source, then sign-ups from those visits, and then revenue from those sign-ups. Viewing the components in this way produces a nifty equation:
Now we can start to plot our segments (that is, the traffic sources) against these component values. In this case, we went with the following bubble chart:
In this chart, we’re plotting the 200 traffic sources that drive the most revenue for us — together, they represent over 95% of our online revenue. The x-axis represents the percent of visitors for each traffic source who signed up for a plan. The y-axis represents the revenue we received per sign up, on average. And the size of the bubble represents the total number of visitors. We also graphed both the y-axis and x-axis along a logarithmic scale, equally spacing 1, 10, 100, and so forth. Depending on the data, logarithmic scales can work better in cases like this, when larger values are spaced further and further apart from each other.
Immediately, we can see that traffic from direct visits and Google searches dwarf our other traffic sources in terms of total visits (and consequently, total revenue as well). They are also somewhat further to the top right than average, which means they achieve higher revenue per visit. This makes sense: visitors who are ready to make a purchase or know what they want are more likely to search for related terms or seek us out directly. Those bubbles are so big, though, that they’re hiding differences among the other sources. We can remove these two data points to see a clearer picture of the remaining traffic sources:
Now we can dig into what the chart shows us about these segments. Take the visitors arriving from Typekit colophons, for example, where a high volume of visitors and strong sign up rates are bolstering a relatively low proportion of paid plans. This tells us that to increase revenue here, we want to focus on improving the proportion of paid plans. That might mean reexamining how we’re presenting the benefits of each plan or perhaps how we’re directing these visitors through the sign-up flow. On the other hand, the Lost World’s Fairs traffic source has the opposite problem — plenty of traffic and a decent proportion of paid plans, but not many sign ups per visit. We know, then, that we should focus on sign up rates for this segment, perhaps through custom landing pages. And lastly, we can see that several web design blogs are sending quality visitors, with both strong sign up rates and a large proportion of paid plans, but in low volume. So perhaps we can advertise on sites like these to increase overall traffic.
These are all insights a ranking could never reveal. With this new view, we’ve moved past simply figuring out what’s important to thinking about what we can actually do. We can even draft broad strategies tailored to different areas of the chart:
Examining segments in context like this can also help show when certain opportunities stand out. When we did this analysis last summer, we were pleasantly surprised by how well our blog was performing. In addition to decent traffic volume, both the sign up rate and paid plan proportion were higher than average. So we decided to invest in the blog and prioritized several design and content changes.
To better integrate the blog and encourage more browsing into the Typekit site, we added our site-wide navigation to the blog header. To increase sign up rates, we improved our promotional material, including a more prominent message box in the top right and a new footer, as well as a list of recent fonts in the right sidebar. We also thought more about the content. Realizing that posts about new fonts were driving strong traffic, we made them even better. We put more time into making our font specimen images larger and more colorful, and we started suggesting font pairings as well. We also introduced a new series of posts, About Face, where we could feature more content like this. Here’s a brief look at the before and after:
It paid off. Before we made those changes, 9% of visitors to our blog were clicking into typekit.com, leading to 4 cents in revenue per blog visit. Today, 27% click into typekit.com, and we see 10 cents in revenue per blog visit. Added to increased traffic overall, our blog is now driving about 190% more revenue per month.
Of course, we didn’t necessarily need the chart to know we could improve our blog. We’re always aware of lots of things we’d like to do when we can get around to it. But we do need charts like this to make sense of our options — to understand how they relate to each other so we can make better decisions about our priorities and approach. That’s where this technique is most beneficial. By simplifying our focus to one metric and then looking at how it breaks apart, we can see which items have the most potential, learn what specific areas need attention, and think of smarter ways to improve.
Together with the technique described in our last post, these methods can help us dive into our data and explore what insights it has to offer. It’s a process that involves asking general questions and looking at what happens when we spread the answer out in different ways. But just as important as it is to begin with questions and dive deeper, we also need to constantly monitor activity at a higher level so we can quickly catch when issues arise. In our next post, we’ll discuss our approach to dashboard metrics and how we go about building team-wide transparency into what’s happening with our users and product on an ongoing basis.
December 5, 2011
This is the first in a series of posts from Typekit’s resident data analyst, Mike Sall.
Data is an incredibly valuable resource, but translating it into something useful isn’t always straightforward. Actually, it’s a lot like apartment hunting on Craigslist: you can’t always trust the postings, the photos can be deceptive, and a lot of information is missing. But after checking out enough listings, you start to get a feel for the market. It becomes easier to spot the best options. And you might even learn to ask about new things, like the best local grocery or the easiest place to find parking.
At Typekit, we approach our data in much the same way. We might not know exactly what we are looking for, so we want to be able to discover the things that matter. At the same time, though, we need to be careful about how we interpret what we see.
To do that, our method is threefold: first, we ask generalized questions; second, we illustrate the answers to those questions across many dimensions; and third, we focus on the trends they reveal rather than any single, potentially distorted value.
It’s an exploratory approach that involves simple calculations and visual illustrations. Like apartment hunting, it’s an iterative process. And it runs the risk of oversimplification, since it doesn’t offer the same level of precision that heavy statistical algorithms might. But if you’re cautious, and you focus on trends rather than single values, you can unearth far more valuable insights in the process. Plus, you can pretty much do everything in a basic spreadsheet.
So, how do we put it into practice? In this series we’ll detail four techniques we use to guide us.
The answer is never black and white, so work towards shades of gray
Frequently, the biggest questions that data can help us answer concern understanding customer behavior. These can cover a wide range of topics. For example, what kinds of products are customers buying? Or, how are they interacting with different features?
To show how we approach these kinds of questions, let’s walk through one that is very important to us at Typekit: how many of our customers are cancelling their subscriptions? We put a lot of effort into understanding cancellation behavior because we want to keep our customers happy. If something is driving our customers to cancel, we need to know about it.
To start tackling this question, let’s look at the equation we need to use:
Thankfully this equation is pretty simple — we only need two numbers!
But as soon as we take the next step and look for those numbers, we run into all sorts of new questions. Should we include the customers who used our beta version? Does it still count if the customer renewed for two years before cancelling? Does it make sense to include the customers who cancelled before we shipped a major feature? What if customers cancelled within a couple minutes of signing up — should we still pool them together with the customers who tried us out for a few months?
Of course, we could answer these questions one by one, imposing limitations on who to include until we had a “typical” population of customers, but the result would be totally myopic. For all we know, some of the most interesting insights might be found among the customers that we excluded.
So, instead of trying to shove the data into a single black and white answer, it’s better to spread it out. The shades of gray are a good thing; given our generalized question, we want to find ways to answer it across multiple dimensions.
That’s when all those questions we run into become an asset. Looking over them, they seem to converge on two basic factors: the point in time when customers signed up, and the duration for which they had their subscription before cancelling. Ah ha! Now we have our dimensions, and we can start plotting the cancellation percentage across them.
After trying out several different groupings and visualizations, here’s the chart we ended up with:
Let’s walk through this chart. On the x-axis, we have the months when customers signed up. So, the area above Jan ’11 represents all the customers who signed up during that month. On the y-axis, the total height of the area represents the total percentage of customers who cancelled. We then split that percentage into stacked bands that represent the different durations for which the customers had their subscriptions before cancelling. For example, the light green band on the bottom represents all the customers who cancelled within a day of signing up. Above that, the darker green band represents all the additional customers who cancelled within the 30-day trial period but after the first day.
Now we can really explore what the chart reveals. Most prominently, cancellations appear to happen at three specific points in time: the 30-day trial period, the year-end renewal mark, and later when enough failed payment attempts essentially render a customer inactive. Within the 30-day trial period, customers act quickly, with around a third of those cancellations occurring on the first day alone. These numbers are changing, however. The overall cancellation percentage of older customers has been decreasing, mostly due to fewer cancellations at the renewal mark, while failed payment attempts have remained steady. Conversely, cancellations prior to the renewal mark have increased since last year, particularly around last November. Still, these trends are separate from the unique behavior we see in our earliest customers — a spike in failed payments but also fewer initial cancellations (likely attributed to the extra patience of early adopters).
All put together, this is incredibly valuable. It represents a multifaceted understanding of our customers’ cancellation behavior. To improve customer retention, we know there are specific points in time when we can focus additional messaging or improvements. On the first day especially, when customers make quick decisions based on initial impressions, we need to nail that on-boarding experience. Likewise, we know there are large swathes of time when customers are not making these decisions, so we don’t need to focus our attention there.
On that point, now that we know how cancellations are distributed across these periods of time, we can better prioritize our efforts. If we think the renewal period cancellations seem high, for example, we might try out different notification messages or re-examine how we’re welcoming customers back to their account settings. As for initial cancellations, we might take a closer look at the increase we’re seeing; we added some major functionality to our transaction system around November of last year, so perhaps some new step or message produced an unwanted side effect.
The chart also leads to additional questions. For instance, how do these trends and distributions differ for customers who have upgraded or downgraded, or for each of our individual plans? When we look at some of these more specific segments, we find even more differences:
It appears that a larger portion of our Personal Plan customers cancel, especially early on during the free trial period, so we can tailor messaging specifically to these users at this time. It also looks like the increase in cancellations prior to the renewal mark is limited to Portfolio Plans, so we can focus improvements on those customers. And for Performance Plan customers, we can feel comfortable making few changes since we see very little cancellation behavior among them.
The more questions we ask, the more insights we can gain. Plus, this is just what we’re seeing today. We reproduce this analysis on a regular basis, so if any of these trends changes significantly, we’ll see it, and we’ll be able to react.
That’s the beauty of quantifying values like these across other dimensions — it allows us to quickly examine the whole landscape of customer behavior. And beyond that, it can reveal answers to questions we never thought to ask. In this case, we weren’t initially asking how specific groups of customers were cancelling at specific times, but now we’re acting on those discoveries.
Still, this particular technique has its limitations. It works best when we want to understand all our customers generally or the differences between just a few groups, like our three subscription plans. When there are many more categories, such as customers from different countries or the results of different advertising messages, it can become burdensome. In the next post we’ll discuss how we approach that end of the spectrum.