Sunday , January 19 2020
Home / Bank of International Settlement / How do machine learning and non-traditional data affect credit scoring? New evidence from a Chinese fintech firm

How do machine learning and non-traditional data affect credit scoring? New evidence from a Chinese fintech firm

Summary:
BIS Working Papers  |  No 834  |  19 December 2019 by  Leonardo Gambacorta, Yiping Huang, Han Qiu and Jingyi Wang PDF full text (314kb)  |  24 pages Focus 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. Contribution Using proprietary transaction-level data from a leading Chinese

Topics:
International Settlement considers the following as important:

This could be interesting, too:

Omkar Godbole writes SNB can leverage its balance sheet if needed, Schlegel says

Amol Agrawal writes More on Govt’s usage of WMA..

Cash writes Hartnäckige Frankenstärke – Auf der Suche nach den mysteriösen Franken-Käufern

Amol Agrawal writes History of RBI’s Ways and Means Advances to Central Government: Old Wine in New Bottle?

BIS Working Papers  |  No 834  | 
19 December 2019
PDF full text
 (314kb)
 |  24 pages

Focus

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.

Contribution

Using proprietary transaction-level data from a leading Chinese fintech company for the period between May and September 2017, we test 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, we analyse the case of an exogenous change in shadow banking regulation in China that caused lending to decline and credit conditions to deteriorate.

Findings

We find 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.


Abstract

This paper compares the predictive power of credit scoring models based on machine learning techniques with that of traditional loss and default models. Using proprietary transaction-level data from a leading fintech company in China for the period between May and September 2017, we test the performance of different models to predict losses and defaults both in normal times and when the economy is subject to a shock. In particular, we analyse the case of an (exogenous) change in regulation policy on shadow banking in China that caused lending to decline and credit conditions to deteriorate. We find that the model based on machine learning and non-traditional data 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.

JEL codes: G17, G18, G23, G32

Keywords: fintech, credit scoring, non-traditional information, machine learning, credit risk

International Settlement
The Bank for International Settlements (BIS) is an international company limited by shares owned by central banks which "fosters international monetary and financial cooperation and serves as a bank for central banks". The BIS carries out its work through subcommittees, the secretariats it hosts and through an annual general meeting of all member banks. It also provides banking services, but only to central banks and other international organizations. It is based in Basel, Switzerland, with representative offices in Hong Kong and Mexico City.

Leave a Reply

Your email address will not be published. Required fields are marked *