A Review of Alternative Data in Credit Risk

Abstract

With the increasing number of loans given to people who previously have no credit history, the current credit risk prediction models trained by conventional data, namely credit history, social capital, etc., have become less effective. The aim of this essay is to figure out how alternative data is used in credit risk evaluation from those published essays. Based on EBSCO and ScienceDirect serving as the main database sources, we filter out 24 most relevant essays. We conclude that the alternative data can considerably optimize the verdict risk prediction models, as well as solve current financing conundrum when it comes to using alternative data to train the prediction models. However, the quality of alternative data and its ethical issues should require further investigations.