The FDIC’s Center for Financial Research has issued a research paper that discusses the use of the information contained in a “digital footprint,” meaning the information that people leave online by accessing or registering on a website, for predicting consumer default.

The researchers considered ten digital footprint variables that included:

  • The device type (e.g. tablet or mobile)
  • The operating system (e.g. iOS or Android)
  • The channel through which a customer comes to a website (e.g. search engine or price comparison site)
  • Two pieces of information about the user’s email address (e.g. includes first and/or last name and includes a number)

According to the researchers, the results of their research suggest that “even the simple, easily accessible variables from the digital footprint proxy for income, character and reputation are highly valuable for default prediction.”  For example, ownership of an iOS device was found to be one of the best predictors for being in the top quartile of income distribution, customers coming from a price comparison website were found to be almost half as likely to default as customers directed to the website by search engine ads, and customers having their names in the email address were found to be 30% less likely to default.  The researchers also found that digital footprint information complements rather than substitutes for credit bureau information, suggesting that a lender that uses information from both sources can make superior lending decisions.

The researchers observe that “digital footprints can facilitate access to credit when credit bureau scores do not exist, thereby fostering financial inclusion and lowering inequality.”  They indicate that their results “suggest that digital footprints have the potential to boost financial inclusion to parts of the currently two billion working-age adults worldwide that lack access to services in the formal financial sector.”

The researchers also comment that regulators are likely to closely watch the use of digital footprints, noting that U.S. lenders using digital footprint information “are likely to face scrutiny whether the digital footprint proxies for [borrower characteristics such as race and gender that may not be considered under the Equal Credit Opportunity Act] and therefore violate fair lending laws.”