BIS published a working paper that examines how machine learning and non-traditional data affect credit scoring. The 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. The results show 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.
Using proprietary transaction-level data from a leading fintech company in China for the period between May and September 2017, the authors tested the performance of different models to predict losses and defaults, both in normal times and when the economy is subject to a shock. They analyzed the case of an (exogenous) change in regulation policy on shadow banking in China that caused lending to decline and credit conditions to deteriorate. The main conclusions of the paper can be summarized as follows:
- The machine learning-based credit scoring models outperform traditional empirical models (using both traditional and non-traditional information) in predicting borrowers’ losses and defaults.
- Non-traditional information improves the predictive power of the model.
- While the models perform similarly well in normal times, the model based on machine learning is better able to predict losses and defaults following 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 the event of a shock.
- The predictive power of all the models improves when the length of the relationship between bank and customer increases. However, the comparative advantage of the model that uses the fintech credit scoring technique based on machine learning tends to decline when the length of the relationship increases.
Keywords: International, China, Banking, Machine Learning, Credit Scoring, Fintech, Credit Risk, Big Data, BIS
APRA has concluded its review of the comprehensive plans of authorized deposit-taking institutions for the assessment and management of loans with repayment deferrals.
ESAs (EBA, EIOPA, and ESMA) published the first joint report that assesses risks in the financial sector since the outbreak of the COVID-19 pandemic.
BoE and HM Treasury confirmed that the COVID Corporate Financing Facility (CCFF) will close for new purchases of commercial paper, with effect from March 23, 2021.
ECB published a decision allowing the euro area banks under its direct supervision to exclude certain central bank exposures from the leverage ratio.
ESAs launched a survey seeking feedback on the presentational aspects of product templates under the Sustainable Finance Disclosure Regulation (SFDR or Regulation 2019/2088).
ECB published input of the European System of Central Banks (ESCB) into the EBA feasibility report on reducing the reporting burden for banks in EU.
EC adopted a decision determining, for a limited period of time, that the regulatory framework applicable to central counterparties, or CCPs, in the UK and Northern Ireland is equivalent to the requirements laid down in the European Market Infrastructure Regulation (EMIR or Regulation 648/2012).
EBA has decided to phase out the guidelines on legislative and non-legislative moratoria of loan repayments, in accordance with the earlier specified end of September deadline.
EBA published an Opinion addressed to EC to raise awareness about the opportunity to clarify certain issues related to the definition of credit institution in the upcoming review of the Capital Requirements Directive and Regulation (CRD and CRR).
ECB finalized the guide on assessment methodology for the internal model method for calculating exposure to counterparty credit risk (CCR) and the advanced method for own funds requirements for credit valuation adjustment (A-CVA) risk.