segunda-feira, 23 de agosto de 2021

Using digital footprint to predict financial behavior in the distant future with significant accuracy


"Abstract The authors present empirical evidence that borrowers, consciously or not, leave traces of their intentions, circumstances, and personality traits in the text they write...This textual information has a substantial and significant ability to predict whether borrowers will pay back the loan...The authors use text-mining and machine learning tools to automatically process and analyze the raw text in over 120,000 loan requests ...The authors further observe that defaulting loan requests are written in a manner consistent with the writing styles of extroverts and liars"  

A more recent paper by researchers at German universities used 250,000 observations, to show that even simple, easily accessible variables from the digital footprint match the information content of credit bureau scores. The authors wrote that "...the use of digital footprints thus has the potential to boost access to credit for some of the currently 2 billion working-age adults worldwide who lack access to services in the formal financial sector" https://academic.oup.com/rfs/article/33/7/2845/5568311?login=true