Featured Product

    BIS Paper Examines How Non-Traditional Data Affect Credit Scoring

    December 19, 2019

    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
    News

    BCBS Amends Guidelines on Sound Management of AML/CFT Risks

    BCBS amended the guidelines on sound management of risks related to money laundering and financing of terrorism (ML/FT).

    July 02, 2020 WebPage Regulatory News
    News

    US Agencies Finalize Amendments to Swap Margin Rule

    US Agencies (Farm Credit Administration, FDIC, FED, FHFA, and OCC) finalized changes to the swap margin rule to facilitate implementation of prudent risk management strategies at banks and other entities with significant swap activities.

    July 01, 2020 WebPage Regulatory News
    News

    PRA Letter Sets Expectations on Approach to Managing Climate Risks

    PRA published a letter that builds on the expectations set out in the supervisory statement (SS3/19) on enhancing banks' and insurers' approaches to managing the financial risks from climate change.

    July 01, 2020 WebPage Regulatory News
    News

    EBA Guidelines on Treatment of Structural Foreign Exchange Under CRR

    EBA finalized the guidelines on treatment of structural foreign-exchange (FX) positions under Article 352(2) of the Capital Requirements Regulation (CRR).

    July 01, 2020 WebPage Regulatory News
    News

    FSB Issues Statement on Impact of COVID-19 Crisis on Benchmark Reform

    FSB published a statement on the impact of COVID-19 pandemic on global benchmark transition.

    July 01, 2020 WebPage Regulatory News
    News

    IAIS Publishes List of Internationally Active Insurance Groups

    IAIS published the list of Internationally Active Insurance Groups (IAIGs) publicly disclosed by group-wide supervisors.

    July 01, 2020 WebPage Regulatory News
    News

    FED Temporarily Revises FR Y-9C With Respect to PPPLF and CARES Act

    FED has temporarily revised the reporting form on consolidated financial statements for holding companies (FR Y-9C; OMB No. 7100-0128).

    July 01, 2020 WebPage Regulatory News
    News

    EC Launches Consultation on Review of Solvency II Directive

    EC launched a consultation on the review of the key elements of Solvency II Directive, with the comment period ending on October 21, 2020.

    July 01, 2020 WebPage Regulatory News
    News

    ECB Consults on Supervisory Approach to Consolidation in Banking

    ECB launched a consultation on the guide that sets out supervisory approach to consolidation projects in the banking sector.

    July 01, 2020 WebPage Regulatory News
    News

    IAIS on Package for 2020 Data Collection on ICS and Aggregation Method

    IAIS published technical specifications, questionnaires, and templates for 2020 Insurance Capital Standard (ICS) and Aggregation Method data collections.

    June 30, 2020 WebPage Regulatory News
    RESULTS 1 - 10 OF 5425