The Eyes Have It: GazeHawk Introduces Low-Cost Eye Tracking Studies for Web Designers

8/17/10Follow @wroush

This is the third in a series of profiles of companies emerging this summer from Mountain View, CA-based startup incubator Y Combinator.

In e-commerce, understanding the psychology of the all-important click is more art than science. No one knows for sure what stimulates Web page visitors to click on certain links and not others; all Web usability experts can really do is quantify the way people behave, and experiment from there. And for that purpose, the most valuable kind of research, apart from tracking actual clicks, is studying where users direct their gaze on a Web page. After all, as GazeHawk co-founder Brian Krausz puts it, “The first step in getting people to click on an ad is to get them to look at it.”

The mission at GazeHawk, a Mountain View, CA-based startup funded by Y Combinator this summer, is to make so-called “eye tracking” data more easily available to Web publishers, through what might be called a quick-and-dirty approach to data capture. The gold standard in eye tracking, says Krausz’s fellow founder Joe Gershenson, is “bright pupil” technology, in which an infrared beam is aimed at a user’s eye, and the reflections are measured to calculate the eye’s angle with respect to a computer screen. From the angle, it’s possible to derive what part of the screen the user is looking at. Bright pupil systems create lots of pretty data—heatmaps showing where users’ eyeballs traveled across a Web page and where they lingered—but the equipment costs $40,000 or more, and eye-tracking consultants charge $5,000 or more per study, according to Krausz. GazeHawk’s innovation is to get that cost down to $49 per study, using equipment no fancier than a conventional webcam.

GazeHawk heatmap for WakeMate.comThat could not only put a lot of expensive eye-tracking consultants out of their jobs, but give small Web publishers and e-retailers access insights into the performance of their own websites that only bigger Web companies could afford up to now. “All of the big companies, the Yahoos and Googles, do [eye tracking studies] because $40,000 is nothing to them,” says Krausz. “It’s been distinctly relegated toward this niche, and that’s what we would like to change.”

At GazeHawk.com, Web publishers can get an eye-tracking study going simply by entering the URL of the Web page they’d like to analyze. GazeHawk will outsource the study to as many testers as the customer wants—one tester for $49 per Web page, 10 testers for $490, 20 for $780, and so forth. (Editor’s Note: As an exclusive offer for Xconomy’s business readers, Krausz has set up a temporary 50 percent discount. The code for the discount is XCONOMY10.) The startup has recruited a panel of several hundred testers who conduct the studies remotely from their own desktop or laptop computers.

Testers are paid $4 per page, Mechanical Turk-style, assuming they return usable data. Customers get back a heatmap showing where the testers’ eyes roamed, and for how long. (See the graphic above, which summarizes eye tracking data for the home page at WakeMate, a sleep analysis gadget from Y Combinator-backed Perfect Third.) In theory, that data tells website owners whether the elements designed to attract the most attention—the “Product Tour” or “Order Now” buttons, for example—are performing as hoped. (More on that in a moment.)

Krausz and Gershenson are both 2009 graduates of Carnegie Mellon University. After school, Krausz went to work for Newton, MA-based TripAdvisor, helping to build the company’s recently introduced airfare search tool, while Gershenson went on for a master’s degree in computer science. But the strange magnetism of the startup world pulled them back together.

“I do a lot of things with Internet usability and Web 2.0 stuff, and Joe has amazing skills with these involved algorithms,” says Krausz. “Being good friends, we said ‘There has to be a way to combine these skills to make a successful company.’”

But there was no grand plan. The pair didn’t decided to leave their old posts and launch GazeHawk until after they’d been accepted to Y Combinator, where they’d applied “almost on a whim,” Krausz says. (Getting in “made the decision process on whether to start a company much easier, since it gives you the biggest boost for success I can think of short of being friends with Ron Conway or someone like that.”)

The central insight that Krausz and Gershenson are trying to bring to the Web usability market is that eye tracking data doesn’t have to be perfect to be informative. Older technologies like infrared-based bright pupil systems are expensive in part because they measure pupil angles down to single-pixel resolution, and in part because they work in real time, building a heatmap as the user takes in a page. “The focus has really been on trying to get that real-time, perfect result,” says Gershenson. “But the important thing in this business is not to know exactly which pixel [testers] were looking at in every split second; it’s to answer the question ‘Are my customers looking at this or not?’ We think it’s possible, with current technology, to build a system that answers that question well.”

The way Gershenson explains it, GazeHawk’s system starts by recording webcam video as a tester’s eyes follow a moving red dot on the screen. It’s a way of sampling what the tester’s eye looks like to the camera when he or she is looking at different parts of the screen. During an actual study, determining where testers are looking is a matter of comparing the new pupil angles to the known positions and calculating the difference.

That’s a bit of an oversimplification, of course. In practice, there’s a lot more going on: Gershenson developed machine learning algorithms, for example, that help eliminate the effect of noise and errors from the often-grainy video signals produced by webcams. But one key to the system is that the tester’s machine merely records video files, which are then uploaded to GazeHawk’s servers for processing into finished heatmaps. That can be done at a relatively leisurely pace. “We realized that Web usability is not a field where real-time feedback is necessary,” says Gershenson.

At $49 per tester per page (and $39 for bigger studies), GazeHawk’s service could inspire a lot of Web developers and e-commerce managers to try eye tracking for the first time, in much the same way that companies like Amesbury, MA-based Performable are making it far easier for small businesses to do A/B testing and multivariate testing—automated methods for gauging Web visitors’ responses to various design and content choices. But there may be one built-in limit on the rate of GazeHawk’s growth, and that’s the difficulty of drawing actionable lessons from eye-tracking studies.

Part of the reason eye-tracking consultants charge so much is that they’re trained in the arcane art of interpreting heatmaps and suggesting attention-getting changes in the size or placement of various page elements. (Consulting services are also frequently provided as an “upsell” by the companies that make eye-tracking equipment, Krausz says.) While GazeHawk does provide personalized recommendations with each heatmap, it’s not one of Krausz and Gershenson’s specialties.

“We will try to give custom advice [to customers] based on the conclusion of their studies,” says Gershenson. “We’ll say, ‘We noticed people aren’t looking at this, and that’s a problem that often crops up because of X, Y, or Z. But a lot of questions about eye tracking are really open. If you look at the best UX [user experience] blogs, there is an open argument about how useful eye tracking is for different things. But we think that by offering this at a significantly reduced cost, we will allow more people to try it, and maybe start adding to the conversation about what you do when you see a certain problem.”

For now, says Krausz, the startup’s first priority is to get its technology working cost-effectively. In part, that means training testers better and lowering the proportion of study data that has to be discarded due to problems like poor calibration and unsuitable lighting conditions. (GazeHawk eats the costs of unusable eye-tracking recordings.)

In fact, Krausz and Gershenson have been so busy optimizing the eye-tracking algorithms that they haven’t yet had a chance to run eye-tracking studies on the GazeHawk.com website. “We love eating our own dog food, and other Y Combinator companies have been using the product,” says Krausz. “But our own website design was finished only a couple of days before we launched. I expect we’ll iterate that as soon as the launch hype is past.”

Wade Roush is a contributing editor at Xconomy. Follow @wroush

By posting a comment, you agree to our terms and conditions.