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 finalized the reporting standard ARS 115.0 on capital adequacy with respect to the standardized measurement approach to operational risk for authorized deposit-taking institutions in Australia.
ESAs Issue Advice on KPIs on Sustainability for Nonfinancial Reporting
EBA is consulting on the implementing technical standards for Pillar 3 disclosures on environmental, social, and governance (ESG) risks, as set out in requirements under Article 449a of the Capital Requirements Regulation (CRR).
EU published Directive 2021/338, which amends the Markets in Financial Instruments Directive (MiFID) II and the Capital Requirements Directives (CRD 4 and 5) to facilitate recovery from the COVID-19 crisis.
The EBA Single Rulebook question and answer (Q&A) tool updates for this month include answers to ten questions.
ESMA updated the set of questions and answers (Q&A), along with the reporting instructions and an XML schema for the templates set out in the technical standards on disclosure requirements, under the Securitization Regulation.
EU published Regulation 2021/337, which amends the Transparency Directive (2004/109/EC), regarding the use of the single electronic reporting format for annual financial reports.
The Standing Committee of the European Free Trade Association (EFTA) recommended that a systemic risk buffer level of 4.5% for domestic exposures can be considered appropriate for addressing the identified systemic risks to the stability of the financial system in Norway.
In a recent statement, PRA clarified its approach to the application of certain EU regulatory technical standards and EBA guidelines on standardized and internal ratings-based approaches to credit risk, following the end of the Brexit transition.
In a recently published letter addressed to the G20 finance ministers and central bank governors, the FSB Chair Randal K. Quarles has set out the key FSB priorities for 2021.