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
EBA Publishes Final Regulatory Standards on STS Securitizations
The European Banking Authority (EBA) published the final draft regulatory technical standards specifying and, where relevant, calibrating the minimum performance-related triggers for simple.
ECB Further Reviews Costs and Benefits Associated with IReF
The European Central Bank (ECB) is undertaking the integrated reporting framework (IReF) project to integrate statistical requirements for banks into a standardized reporting framework that would be applicable across the euro area and adopted by authorities in other EU member states.
BCBS to Finalize Crypto Rules by End-2022; US to Propose Basel 3 Rules
The Basel Committee on Banking Supervision met, shortly after a gathering of the Group of Central Bank Governors and Heads of Supervision (GHOS), the oversight body of BCBS.
IOSCO Welcomes Work on Sustainability-Related Corporate Reporting
The International Organization of Securities Commissions (IOSCO) welcomed the work of the international audit and assurance standard setters—the International Auditing and Assurance Standards Board (IAASB)
EBA Publishes Funding Plans Report, Receives EMAS Certification
The European Banking Authority (EBA) has been awarded the top European Standard for its environmental performance under the European Eco-Management and Audit Scheme (EMAS).
MAS Launches SaaS Solution to Simplify Listed Entity ESG Disclosures
The Monetary Authority of Singapore (MAS) set out the Financial Services Industry Transformation Map 2025 and, in collaboration with the SGX Group, launched ESGenome.
BoE Allows One-Day Delay in Statistical Data Submissions by Banks
The Bank of England (BoE) published a Statistical Notice (2022/18), which informs that due to the Bank Holiday granted for Her Majesty Queen Elizabeth II’s State Funeral on Monday September 19, 2022.
ACPR Amends Reporting Module Timelines Under EBA Framework 3.2
The French Prudential Control and Resolution Authority (ACPR) announced that the European Banking Authority (EBA) has updated its filing rules and the implementation dates for certain modules of the EBA reporting framework 3.2.
ECB Paper Discusses Disclosure of Climate Risks by Credit Agencies
The European Central Bank (ECB) published a paper that examines how credit rating agencies accepted by the Eurosystem, as part of the Eurosystem Credit Assessment Framework (ECAF)
APRA to Modernize Prudential Architecture, Reduces Liquidity Facility
The Australian Prudential Regulation Authority (APRA) announced reduction in the aggregate Committed Liquidity Facility (CLF) for authorized deposit-taking entities to ~USD 33 billion on September 01, 2022.
