There's Gold in 'Reality Mining'

Data from the use of cell phones and other mobile devices yield patterns of movement that can help public agencies and businesses

In the aftermath of the September 11 attacks, U.S. officials scrambled to secure other national landmarks that might become future targets. Chief among them: California's Golden Gate Bridge. Might terrorists try to destroy the passageway between San Francisco and Marin County, and if so, how widespread would the fallout be?

To answer those questions, the Homeland Security Dept. turned to a small company called Inrix, which was recently spun out of Microsoft (MSFT) and uses GPS-enabled mobile phones and tracking devices installed on commercial vehicles to monitor traffic conditions. Inrix used its models to predict that the loss of the 1.7-mile bridge would result in immediate transport chaos. But less predictably, Inrix found that the region would bounce back quickly. "On Days Two through Four, the system tends to adjust because people know what is happening and adjust their plans," Inrix CEO Bryan Mistele says.

Inrix was able to reach those conclusions using what's known as "reality mining," or the study of human interaction based on usage of mobile phones and other portable computing devices. Researchers say they can get a more accurate picture of what people do, where they go, and with whom they communicate from a device they carry than from more subjective sources, including what people say about themselves. In short, people lie—cell phones don't. Or so the thinking goes.

Detecting Trends for the Common Good

These ubiquitous mini-computers not only log calls and messages, but when equipped with GPS chips can record a person's whereabouts. Using Bluetooth, the short-range technology that forges wireless connections between electronics, the phone can also keep tabs on the user's proximity to other holders of similar phones, and as more people use wireless handsets to make purchases, the phone gathers data on spending patterns, too.

Researchers can use this trove not only to gird for such doomsday scenarios as a terror attack but also for practical business purposes, like helping companies foster interoffice cooperation, event planners manage multimillion-dollar conventions and conferences, and cell-phone companies provide better customer service.

Reality mining can also help city planners unravel traffic snarls and public health officials track and prevent the spread of illnesses, such as severe acute respiratory syndrome, or SARS. "There is so much societal good that can come from this," says Sandy Pentland, a Massachusetts Institute of Technology professor and reality mining pioneer. "Suddenly we have the ability to know what is happening with the mass of humanity and adapt society to accommodate the trends we can detect, and make society work better."

Useful Data Patterns

Cell phones can be particularly useful in gathering health-related information, says Alex Kass, a researcher at Accenture (ACN). "It's one of the application areas that focus well both on the individual and on large groups," he says. Researchers can use data on a sample population over a given period—say, a week or a month—and then assume some of them are sick, to provide a more accurate picture of how widely an illness could spread, Kass says. Information on a particular individual or group could help build more accurate models to predict how an illness spreads from one person to another. People could also use the data to keep better tabs on themselves, Kass says.

Inrix tracks some 750,000 vehicles traversing 55,000 miles of roadway in 129 cities to gather real-time traffic congestion data that is then used in a variety of ways, such as providing live traffic information to devices made by Garmin (GRMN) and TomTom.

Over time, all that data shows useful patterns. "We can build a model for major sporting events that shows what happens if you build the stadium in one place or another," Inrix CEO Mistele says. "We've found that in most cities the biggest determining factor in traffic is school schedules. In other cases, like Washington, D.C., the legislative calendar is very important. We can correlate our data to practically any other variable."

Other business implications of reality mining are legion. Nathan Eagle is a research scientist at the MIT Design Laboratory who works with Pentland. Eagle is currently working with a database that holds an entire month's worth calling data for a whole European country, though he won't say which one. Scrubbed of all information that might be used to identify people, the data set contains information on 250 million phones and some 12 billion phone calls.

Wireless companies could use the information to help keep customers from switching to a rival—a strategic must in a region where most of the population already has a cell phone and "new" customers are scarce. Eagle mines the data for a range of information, such as identifying so-called influencers, who use their phone the most. Not only are these subscribers valuable because they use their phone a lot, but they're also more likely to influence other people's service and product purchases—and to take customers with them when they switch. "If someone who makes a lot of calls walks away, there's a higher potential that they'll take more people along with them," Eagle says. His research is funded in part by Nokia (NOK).

Privacy Objections

Conference organizers are turning to reality mining to ensure events come off without a hitch. One aim of meetings is to ensure participants interact with people from disparate backgrounds, and a planner can use radio-enabled tags to know whether that's happening. "Very often your first inclination at something like this is to hang out with someone you know or who you came with," says Rick Borovoy, founder of nTAG Interactive, a company spun out from MIT in 2002 that specializes in what it calls event data management. "We try to intervene and change that by collecting data on how people are interacting." If people aren't mingling enough, conference organizers can offer incentives—say, a door prize—for whoever circulates the most. Customers include Hewlett-Packard (HPQ), General Electric (GE), Siemens (SI), IBM (IBM), and AT&T (T). "Our customers spend a lot of money on these events, and they want to know whether or not they're effective," Borovoy says.

If all this movement-tracking sounds invasive, that's because it is, privacy advocates say. Guilherme Roschke, a staff attorney at the Electronic Privacy Information Center, or EPIC, in Washington, D.C., says that while reality mining may have some legitimate uses, it can also be abused. He's also concerned when people are monitored without their consent. "There is a lot of new information being collected, and it brings significant new capabilities, some of which are privacy-infringing," Roschke says. "The first thing is to let people know this data is being collected, and how it's going to be used. And whenever it's put to a new use, then it must be disclosed."

The way Eagle sees it, the data is being collected anyway, so why not put it to good use? "Right now practically the only use for it is for law enforcement to use it to investigate crimes and put people in jail," he says. "I just think it can be put to better use to deliver services that are interesting or that help people."

Before it's here, it's on the Bloomberg Terminal. LEARN MORE