Financial technology (fintech) is taking on an ever more important role in lending decisions. This paper compares the predictive power of credit scoring models based on machine learning techniques, as used by fintech companies, with that of traditional loss and default models typically used by banks.
Using proprietary transaction-level data from a leading Chinese fintech company for the period between May and September 2017, researchers tested the ability of different models to predict losses and defaults both in normal times and when the economy is subject to a shock. In particular, they analyse the case of an exogenous change in shadow banking regulation in China that caused lending to decline and credit conditions to deteriorate.
They found that the model based on machine learning and non-traditional data used by the fintech company is better able to predict losses and defaults than traditional models in the presence of a negative shock to the aggregate credit supply. One possible reason for this is that machine learning can better mine the non-linear relationship between variables in a period of stress. Finally, the comparative advantage of the model that uses the fintech credit scoring technique based on machine learning and big data tends to decline for borrowers with a longer credit history.