by Steve Smith, Friday, June 1, 2007
MOST BEHAVIORAL TRACKING WORKS ON the simple assumption that past behavior is a solid predictor of future need. Not so in all applications, says Baynote CEO Jack Jia. The founding CTO of content management giant Interwoven took a crash course in social science, which he claims tells us that group behavior in a given context is a better indicator of any given user's future actions than piles of personal behavioral history. He tells us how the wisdom of the crowds in context informs Baynote's approach to content and product recommendations.
Behavioral Insider: You were at content management supplier at Interwoven for eight years. How did that experience evolve into Baynote?
Jia: The last years of my Interwoven experience really helped me start thinking about the bigger problems people were facing. Customers were saying, the more content I am publishing, the less valuable it becomes. People aren't finding it. I created all this stuff but they aren't really getting value. This became the genesis of this new company that helps people consume this content more effectively. It follows how information and knowledge is accumulated and how it is passed down generation to generation.
Behavioral Insider: Explain that connection to human behavior patterns.
Jia: I actually spent almost six months studying and working with some of the social scientists at Stanford, really thinking through to the right solution -- not from a tech or computer science perspective, but more from psychology, sociology and organizational behavior.
We produce content recommendations. Where other people find value with similar things on your site, we start to accumulate that knowledge by observing their behaviors. We can deduce what is useful and what is not. and feed that back to the users with similar needs. The bottom line is the conversion rate improvement for any business site. Our e-commerce customers have seen somewhere in the area of 20%-plus revenue lift. The support side is cost reduction. Fewer people call if they find the answers online. We just did Turbo Tax's support site and they saw a huge reduction of the support costs by having the community being the backbone of providing what answers to provide to which questions.
Behavioral Insider: Explain that connection between the social science you learned at Stanford and the company's behavioral model.
Jia: We found what we call the wisdom of the invisible crowd. This is a big insight that the psychologists and the social scientists have known for years. There is a controversy between behavioral targeting and contextual targeting. A lot of computer scientists believe you can predict people based on their past behaviors, that past needs can actually dictate what I want in the future. And that's really the basis of personalization and the more recent BT.
When we went to Stanford and really studied this, we found [past behavior] is a very poor predictor, because humans have way too many profiles. I am a father, a son, a brother, I like travel, I like a lot of things. You can track all my past behaviors all you want, but in any given moment when I go onto a site it is very hard for you to predict what I want. We believe that particular approach has a low accuracy in terms of predicting human behavior.
However, there is opposite research that is well known among scientists that asks whether people are unique. We are raised with the notion that I am unique and don't have needs quite like other people. But the scientists proved we are not unique at all. We are pack animals. Pretty much 95% of people will need the same thing. We only need to find out under what context what things are useful, and then present that product or content given the context. Then the prediction is very accurate.
Behavioral Insider: Describe how that insight translates into a recommendation method.
Jia: For example, although we know each individual and track them, we don't really care what they did yesterday. We can build profiles, but generally we don't use that primary guidance. Instead, say at our customer Cisco's site, someone goes to the router portion of the site -- then you will more than likely behave like other people who have interest in routers. There is a router peer group vs. the switches Cisco also sells, or the investor visitors vs. the job seeker. They can be the same people with different profiles, but once you enter that router world you behave much like the other people in routers.
We don't really care about your behaviors. And given our attention is so short, we can only recommend to you three or four documents before you get impatient. And then which ones you choose is very important. In aggregate, you are watching everyone's behavior. But it's not necessary to track behaviors day after day.
Behavioral Insider: But what data points are you collecting to understand what people will do in a given context?
Jia: That's one of the unique things. Almost all of the vendors out there except Amazon is collecting clicks. Through our studies at Stanford we found the click doesn't tell you anything. The click is the function of the area of the site you are on. If you put a link on the front page, you will get more clicks. It is a self-fulfilling prophecy. If you link less-used content on the front page more people will click on it, and then people back out of it.
So click doesn't tell whether a piece of content is useful or not. It is the other things we are tracking, about 20 behavioral characteristic that in aggregate can tell us, for instance, how much time you spent on a piece of content relative to the size of the content. It really depends on what other like-minded peers also spent time with. Whether you come back to the same content. A repeat visit to the three or four products you like, we call virtual bookmarking. So, basically how you navigate now is telling.
Behavioral Insider: What kind of sample base is needed to make predictions?
Jia: One person can be noisy. Two people still noisy. Three to 10 with similar needs, like-minded peers, will start to cancel the noise out. By observing a set of heuristics, that forms a unique fingerprint of someone who likes or dislikes the content. Then we compare that fingerprint with like-minded peers, 10 or 100 other people. The noise will cancel each other out in 100, and what remains is a consistent pure signal. That is where we know that this content is truly important to that group of people.
NEW YORK — Personal identity has taken on a new meaning in the digital age, where basic facts like your name, address or age are far less important to some people than the collected records of what you were looking at online.
Technologies for monitoring and interpreting Internet habits as a predictor of future behaviour cropped up at the start of this century, but only now are gaining momentum as the newest gold mine for Web sites and their advertisers.
Known as behavioural targeting, the premise is to follow the sites you visit and build a picture of what products may interest you, then deliver related advertising in time for you to choose your purchase.
U.S. marketers will nearly double their spending on such advertising to $1-billion (U.S.) next year from $575-million in 2007, according to research firm eMarketer. By 2011, behavioural targeting will surge to nearly $3.8-billion of online ads.
Industry executives say it's a boon to the consumer, who in an ideal world will only receive commercial messages that suit them personally, while enjoying online entertainment or information for free.
“As long as I'm seeing relevant advertising and as long as I am receiving free content, I am a pretty happy person,” said Bill Gossman, chief executive of behavioural targeting firm Revenue Science. The company's clients have included media outlets from Reuters Group Plc to Walt Disney Co.'s ABC News and Gannett Co. Inc.'s USA Today.
To protect individual privacy, U.S. companies who sell such services say they do not link the behavioural data with the actual names and addresses of computer users.
“We have no idea of who that individual is and I don't want to know,” Gossman said. “What marketers want to know is, what is their intent?”
Critics charge the technologies will only stoke corporate efforts to accumulate an ever-increasing pile of data on a person's behaviour whether on the Internet or elsewhere.
“My concern as we give away ever more data about ourselves, our activities, our behaviour in the world, our choices ... is that fairly rich data sets can be built up, maybe not in one place but relationally across the Web,” said Adam Greenfield, a futurist and user experience consultant.
The greater danger, he said, involves the ability to match data on Web behaviour with information such as a person's location, via their cell phones, or commercial transactions.
For a marketer, there is no such thing as too much information when it comes to making a sales pitch.
“The picture isn't complete until you literally plant tracking devices inside somebody's arm,” said Emily Riley, an analyst at JupiterResearch. “When I go to the mall, nobody at Google is going to know what stores I have visited.”
WHAT'S A DEMOGRAPHIC?
For example, a person comparing automobile brands online is likely interested in buying a car. Behavioural targeting narrows those categories further: Is the car a model that would seat a family? Did the individual inquire about hybrid vehicles, suggesting interest in protecting the environment? Did they also look for an infant's safety seat?
From that data, enough information could be gleaned about a person to know that they might be interested in not just the latest Volvo or Honda model, but perhaps biodegradable diapers as well.
“The ideal is where they literally know your preferences and what motivates you,” said Riley. “That is really personalized. If we are at Web 2.0, that would be Web 3.0, where your entire personality is online.”
Build a database of such people's habits and you can index their interests to create an “audience” of individuals. They may be at different places online and in the real world, but they all show a preference for environmentally friendly products, or tend to spend more money on shoes than on hats.
That proposition has turned traditional advertising, long dominated by the television commercial, on its head. In the Golden Age of U.S. advertising, a marketer could be confident that buying time for a commercial on three TV networks would reach a wide swathe of the domestic audience.
Those audiences were defined by demographic categories like age and gender. TV networks based the price of their ads on a small sample of the viewing habits of U.S. consumers, charging their highest premium for programs popular among young males.
As people now get their entertainment on everything from cell phones to video games, the audience has dispersed from their living rooms. That makes them harder to track down, but offers the advantage of more precise information once they are found.
Internet advertising agencies are reaping the advantages of these fundamental changes, largely because they help figure out where to find a specific audience and build campaigns tailored to the Internet as a medium.
“This is going to be a Golden Age of advertising,” said Scott Howe, president of the DRIVEpm behavioral unit of online marketer aQuantive Inc. “It's the ability to deliver messages in sequence and tell a story. Advertising is going to become fun again. It's going to become serialized.”
Howe said behavioural ad campaigns can be just as useful for filtering out certain consumers. In one campaign for a software product, the manufacturer targeted customers who selected the product for their online shopping cart but deleted it before making their final purchase.
The rationale was these customers had already shown interest in the product, and just needed some further incentive to make an order.
“It was the worst-performing campaign. It turned out these people weren't buying the software in the end because it was incompatible” with their computers, he said. The marketer then used the same list of customers to make sure they didn't receive such advertising in the future.
Just try to do that on television.
