WASHINGTON — A new study released Thursday bolsters the case for lenders to use borrowers' digital footprints in assessing their creditworthiness.
The paper, released by the Federal Deposit Insurance Corp.'s Center for Financial Research, said the data trails people leave online — even down to what brand of smartphone they use — are useful at predicting default rates.
"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," wrote the study's four authors.
They even suggested that a digital footprint in some instances can be better at predicting default rates than credit bureau scores. "Interestingly, a model that uses only the digital footprint variables equals or exceeds the information content of the credit bureau score."
But they cautioned that their findings do not suggest lenders should rely just on alternative data types. "We find that the digital footprint complements rather than substitutes for credit bureau information," the paper said.
The findings have significant implications as technology-focused lenders have been developing alternative data models for evaluating borrowers.
The paper suggested even seemingly trivial aspects of a person's digital experience can correspond with their credit profile. For example, the authors claim to see correlation between whether a borrower uses an Apple or Android phone and creditworthiness.
"Android users default more frequently than the baseline category, consistent with the univariate results and consistent with the fact that consumer purchasing an iPhones are usually more affluent than consumers purchasing other smartphones," the study said.
The authors noted that the study is pertinent as more fintech companies are tracking and analyzing online consumer data to offer loans, which can help them gain market share.
“Understanding the importance of digital footprints for consumer lending is of significant importance,” the paper said. “If digital footprints yield significant information on predicting defaults then FinTechs — with their superior ability to access and process digital footprints — can threaten the information advantage of financial intermediaries and thereby challenge financial intermediaries’ business models.”
The study was based on data from more than 270,000 purchases at an e-commerce company in Germany. The data was simply what people leave when they access or register on a website, even without inputting text.
The researchers were able to track whether the online visitor was using an Apple or an Android for the purposes of predicting default rates. A past study has shown that people who own Apple devices are in a higher income distribution, which the FDIC’s study backed.
“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,” the paper said.
The FDIC study also found that customers who came to the website from a price comparison website were “almost half as likely to default” as customers who came from search engine ads. Also, customers who had their names in their email address were 30% less likely to default.
The study determined that using the digital footprint has “the potential to boost financial inclusion” when a consumer has no credit score or a low score.
“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,” the authors said in the paper.
The paper was written by Tobias Berg and Ana Gombović of the Frankfurt School of Finance & Management, Valentin Burg of the Humboldt University Berlin, and Manju Puri of Duke University and the FDIC.
