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
EBA published a report analyzing the impact of the unwind mechanism of the liquidity coverage ratio (LCR) for a sample of European banks over a three-year period, from the end of 2016 to the first quarter of 2020.
In response to questions from a member of the European Parliament, the ECB President Christine Lagarde issued a letter clarifying the possibility of amending the AnaCredit Regulation and making targeted longer-term refinancing operations (TLTROs) dependent on the climate-related impact of bank loans.
IASB started the post-implementation review of the classification and measurement requirements in IFRS 9 on financial instruments and added the review as a project to its work plan.
FSB published a report that examines progress in implementing policy measures to enhance the resolvability of systemically important financial institutions.
EBA published a report on the benchmarking of national loan enforcement frameworks across 27 EU member states, in response to the call for advice from EC.
FSB published a letter from its Chair Randal K. Quarles, along with two reports exploring various aspects of the market turmoil resulting from the COVID-19 event.
RBNZ launched a consultation on the details for implementing the final Capital Review decisions announced in December 2019.
The Trustees of the IFRS Foundation, which are responsible for the governance and oversight of IASB, have announced the appointment of Dr. Andreas Barckow as the IASB Chair, effective July 2021.
HKMA issued a letter to consult the banking industry on a full set of proposed draft amendments to the Banking (Capital) Rules for implementing the Basel standard on capital requirements for banks’ equity investments in funds in Hong Kong.
ESRB published an opinion assessing the decision of Swedish Financial Supervisory Authority (FSA) to extend the application period of a stricter measure for residential mortgage lending, in accordance with Article 458 of the Capital Requirements Regulation (CRR).