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 Finalizes on Climate Risk Guideline, Issues Other Updates
The Office of the Superintendent of Financial Institutions (OSFI) is seeking comments, until May 31, 2023, on the draft guideline on culture and behavior risk, with final guideline expected by the end of 2023.
BIS Paper Examines Impact of Greenhouse Gas Emissions on Lending
BIS issued a paper that investigates the effect of the greenhouse gas, or GHG, emissions of firms on bank loans using bank–firm matched data of Japanese listed firms from 2006 to 2018.
HMT Mulls Alignment of Ring-Fencing and Resolution Regimes for Banks
The HM Treasury (HMT) is seeking evidence, until May 07, 2023, on practicalities of aligning the ring-fencing and the banking resolution regimes for banks.
BCBS Report Examines Impact of Basel III Framework for Banks
The Basel Committee on Banking Supervision (BCBS) published results of the Basel III monitoring exercise based on the June 30, 2022 data.
PRA Consults on Prudential Rules for "Simpler-Regime" Firms
Among the recent regulatory updates from UK authorities, a key development is the first-phase consultation, from the Prudential Regulation Authority (PRA), on simplifications to the prudential framework that would apply to the simpler-regime firms.
DNB Publishes Multiple Reporting Updates for Banks
DNB, the central bank of Netherlands, updated the list of additional reporting requests and published additional data quality checks and XBRL-Formula linkbase documents for the first quarter of 2023.
NBB Sets Out Climate Risk Expectations, Issues Reporting Updates
The National Bank of Belgium (NBB) published a communication on climate-related and environmental risks, issued an update on XBRL reporting
EBA Updates Address Securitization Standards and DGS Guidelines
The European Banking Authority (EBA) published the final draft of the regulatory technical standards that set out conditions for assessment of homogeneity of the underlying exposures in simple, transparent, and standardized (STS) securitizations.
FSB Publishes Letter to G20, Sets Out Work Priorities for 2023
The Financial Stability Board (FSB) published a letter intended for the G20 Finance Ministers and Central Bank Governors, highlighting the work that FSB will take forward under the Indian G20 Presidency in 2023
ISSB Standards May Become Effective from January 2024
The International Organization of Securities Commissions (IOSCO) welcomed the confirmation statement by the International Sustainability Standards Board (ISSB) setting out its progress in the development of its first sustainability-related corporate disclosure standards.
