What does your mobile phone usage say about your credit-worthiness?

By Scott Kirsner, Globe Columnist

Does the number of text messages you send, or the time of day you make your first phone call, say something important about how credit-worthy you are?

Cignifi, a small Cambridge start-up with roots in the UK, believes it does. The company is out raising $2 million in funding to commercialize its technology this year, after a pilot test in Brazil in 2011.

"There's a vast market of consumers in countries like Brazil, China, India, and the Phillipines who want access to financial services like credit cards, loans, or insurance," says Jonathan Hakim, Cignifi's chief executive. "But while they may have jobs, and some have bank accounts, there really is no credit history for them." One thing they do have? Mobile phones.

Cignifi has developed sophisticated modeling software that can look at usage data from consumers' mobile phones and make predictions about who that person is and how they live. There's no single data point — like making lots of short calls between 2 and 5 a.m. every morning — that suggests that someone is a bad credit risk. But Hakim says, "The way you use your phone is a proxy for your lifestyle. It's not random. So we're looking at things like the length of calls, the time of day, and the location you make them from. Also things like whether you top up [a pre-paid SIM card] regularly. We want to see how stable the patterns are. When you look at that, you can create these behavioral clusters that give you information about users' appetite for new [financial] products, and their ability to repay a debt."

Cignifi plans to pitch the technology to financial services firms in Brazil first, and perhaps Mexico next. (The firms would obviously need to hash out a partnership with mobile operators to get access to usage data.) Last year's test in Brazil ran data for three million cell phone users through Cignifi's software, and produced a behavior-based score that resembles the FICO credit score many U.S. consumers are familiar with, which runs from 300 to 850 points. Then, the company compared its predictions about their credit-worthiness against actual credit card debt information for that same group.

"After that big lab experiment in Brazil, the next phase is to go and commercialize it," Hakim says. He describes the start-up as an "arms merchant," providing software that enables financial services companies to sell products profitably to consumers they couldn't previously reach.