Digital Footprints: A New Pathway in Scoring Credit?
According to a new study by the Center for Financial Research (CFR) at the Federal Deposit Insurance Corporation (FDIC), a consumer’s digital footprint (i.e. whether a consumer uses an Apple or Android product, etc.) can do a better job at predicting a consumer’s default rate than a consumer’s credit bureau score.
The authors of the study analyzed more than 250,000 observations looking at ten variables, including the device type (tablet or mobile), the operating system (iOS or Android), and the email service provider (Gmail or Yahoo).
“Our results suggest that even the simple, easily accessible variables from the digital footprint proxy for income, character and reputation and are highly valuable for default prediction,” the authors argue. “For example, the difference in default rates between customers using iOS (Apple) and Android (for example, Samsung) is equivalent to the difference in default rates between a median credit score and the 80th percentile of the credit score.”
This finding is consistent with a 2018 University of Chicago study by Marianne Bertrand and Emir Kamencia that found, “Across all years in our data, no individual brand is as predictive of being high-income as owning an Apple iPhone in 2016.”
The CFR study also found a relationship between default rates and a consumer’s email service provider. Users of Gmail or T-Online tend to have lower default rates than users of Yahoo or Hotmail.
Naturally, these variables stack, so the more digital variables that a lender collects and analyzes, the better. For example, users of Apple phones and Gmail tend to have substantially lower default rates than users of Android phones and Yahoo.
Overall, the CFR study finds that digital footprint variables – data that are readily available to online companies – do a better job at predicting default rates than credit bureau scores. In addition, the study claims that these digital variables can forecast future changes in a consumer’s credit score.
The study argues that this, “provides indirect evidence that the predictive power of digital footprints is not limited to short-term loans originated online, but that digital footprints matter for predicting creditworthiness for more traditional loan products as well.”
Nevertheless, the authors insist that these digital footprints should complement credit bureau scores, and not be used as substitutes. In fact, a lender that utilizes both digital footprints and credit bureau scores can make superior lending decisions relative to their competition.