BIS Paper Examines How Non-Traditional Data Affect Credit Scoring
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.
Related Links
Keywords: International, China, Banking, Machine Learning, Credit Scoring, Fintech, Credit Risk, Big Data, BIS
Related Articles
OSFI Discusses Benchmark Rate Transition, Sets Out Work Priorities
The Office of the Superintendent of Financial Institutions (OSFI) published the strategic plan for 2022-2025 and the departmental plan for 2022-23.
EBA Proposes Standards to Support Secondary NPL Markets
The European Banking Authority (EBA) is consulting, until August 31, 2022, on the draft implementing technical standards specifying requirements for the information that sellers of non-performing loans (NPLs) shall provide to prospective buyers.
EU Confirms Agreement on Rules on Cybersecurity and Banking Resolution
The European Council and the Parliament reached an agreement on the revised Directive on security of network and information systems (NIS2 Directive).
EBA Issues Standards for Crowdfunding Service Providers Under ECSPR
The European Banking Authority (EBA) published the final draft regulatory technical standards specifying information that crowdfunding service providers shall provide to investors on the calculation of credit scores and prices of crowdfunding offers.
EU Confirms Agreement on Rules on Cybersecurity and Banking Resolution
The European Securities and Markets Authority (ESMA) published a paper that examines the systemic risk posed by increasing use of cloud services, along with the potential policy options to mitigate this risk.
EC Consults on PSD2 and Open Finance; EU Reaches Agreement on DORA
The European Commission (EC) published a public consultation on the review of revised payment services directive (PSD2) and open finance.
EC Mandates ESAs to Propose Amendments to SFDR Technical Standards
The European Commission (EC) has issued two letters mandating the European Supervisory Authorities (ESAs) to jointly propose amendments to the regulatory technical standards under Sustainable Finance Disclosure Regulation or SFDR.
EBA Examines Supervisory Practices, Issues Deposits Reporting Template
The European Banking Authority (EBA) published its annual report on convergence of supervisory practices for 2021. Additionally, following a request from the European Commission (EC),
SNB Updates NSFR Forms and FINMA Consults on Operational Risk Circular
The Swiss National Bank (SNB) published Version 1.2 of the reporting forms (NSFR_G and NSFR_P) on the net stable funding ratio (NSFR) of banks, along with the associated documentation.
US Agency Publications Address Basel, Reporting, and CECL Developments
The Farm Credit Administration published, in the Federal Register, the final rule on implementation of the Current Expected Credit Losses (CECL) methodology for allowances