This paper evaluates users’ digital footprints or the information that people leave online by accessing or registering a website to predict consumers’ likelihood of default. Using more than 250,000 observations, the authors show that information gleaned from people’s digital footprint can be equal to or even exceed the information content of credit bureau scores.
FDIC Center for Financial Research Working Paper No. 2018-04
The paper evaluates the impact of aspects of customer-bank relationships on loan default rates. Using a dataset that consists of more than 1 million loans made by 296 German banks, the research finds that banks with relationship-specific information from customers establishing transaction accounts are less likely to experience loan defaults and act differently in screening and monitoring behaviors than banks with no information.