Forget FICO: how data is changing the rules of credit and underwriting

Structure Data 2013 Douglas Merrill ZestFinance Robert Frohwein Kabbage

Until the mid-20th century, a banker’s decision to lend money was based in large part on intuition and relationships. This changed dramatically with the creation of the FICO score — a single metric to decide if anyone was worthy of credit or not.

Today, the FICO score is starting to show its age. This is apparent from a new breed of financier who is capable of tapping thousands of  data sources to make more personal decisions, and who can offer credit in ways that traditional lenders do not. One example is ZestFinance, a new style of underwriting company that uses 70,000 data signals and ten parallel machine learning algorithms to assess personal loans.

Speaking at GigaOM’s Structure Data conference in New York, CEO Douglas Merrill explained that ZestFinance employs a host of untraditional signals — such as whether or not a would-be borrower has read a letter on its website — to determine if someone is credit-worthy.

The company’s tools have also allowed it to make a lively business from “dead” people. These are borrowers who banks believe are deceased on the basis of their FICO score. According to Merrill, these dead make up 10% of ZestFinance’s customer base and their rate of repayment is better than that of the living.

Small business lenders are also making use of non-traditional credit signals. The lending firm Kabbage, for instance, taps into data like a company’s UPS activity to assess their financial health — everything from the volume of shipping to the size of the parcels provide signals about how a firm is doing.

CEO Robert Frohwein, who also spoke at the GigaOM event,  said traditional banks simply do not seek out such signals in the first place, meaning they must rely on a much cruder set of metrics when they evaluate loans.

The extra data signals lead to more successful lending rates and are also making credit more affordable and available than it was before. ZestFinance, for instance, provides the 60 million American who use payday loan companies an alternative to high balloon payment fees. Meanwhile, Kabbage is offering more loans than banks to internet-based businesses and to companies whose executives do not match corporate stereotypes.

Check out the rest of our Structure:Data 2013 live coverage here, and a video embed of the entire session follows below:

[youtube http://www.youtube.com/watch?v=GIx9Jyw0FZk&w=560&h=315]

A transcription of the video follows on the next page

page of 2
loading

Comments have been disabled for this post