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

    APRA Announces Deferral of Capital Reform Implementation

    APRA announced that it is deferring the scheduled implementation of Basel III reforms in Australia by one year.

    March 30, 2020 WebPage Regulatory News
    News

    IFRS Publishes Statement on Its Work During the COVID-19 Crisis

    IFRS, in its statement, emphasized that it shares global concerns about the impact of COVID–19 and is supporting its stakeholders by reconsidering timelines of its meetings and publications, providing information on the application of IFRS 9 on financial instruments, and offering calendar updates on ongoing activities.

    March 27, 2020 WebPage Regulatory News
    News

    US Agencies Announce Changes to SA-CCR and CECL Rules Due to COVID-19

    In light of the recent disruptions in economic conditions due to the COVID-19 outbreak, US Agencies (FDIC, FED, and OCC) announced two actions to allow banking organizations to continue lending to households and businesses.

    March 27, 2020 WebPage Regulatory News
    News

    IAIS Adjusts Work Program to Address Impact of COVID-19 on Insurers

    Considering the impact of COVID-19 outbreak, IAIS announced initial adjustments to its work program to provide operational relief to its member supervisors, insurers, and other stakeholders.

    March 27, 2020 WebPage Regulatory News
    News

    OSFI Announces Regulatory Adjustments to Support COVID-19 Efforts

    OSFI published three targeted industry letters that announce a series of regulatory adjustments to support the financial and operational resilience of federally regulated banks, insurers, and private pension plans in the light of COVID-19.

    March 27, 2020 WebPage Regulatory News
    News

    UK Regulators Announce Measures to Address Impact of COVID-19

    UK Regulatory Authorities published statements and guidance addressed to financial entities on dealing with the impact of the coronavirus (COVID-19) outbreak.

    March 26, 2020 WebPage Regulatory News
    News

    ISDA and Industry Request Delay in Timeline for Initial Margin Rules

    Considering the challenges posed by the COVID-19 pandemic, ISDA submitted a letter on behalf of 21 industry associations and their members requesting BCBS, IOSCO, and global regulators to suspend the current timeline for the initial margin phase-in.

    March 26, 2020 WebPage Regulatory News
    News

    FCA, FRC, and PRA Issue Joint Statement to Address Impact of COVID-19

    In response to the COVID-19 outbreak, FCA, the Financial Reporting Council (FRC), and PRA have announced a series of actions and made statements to support the continued functioning of capital markets in the UK.

    March 26, 2020 WebPage Regulatory News
    News

    EC Rule Corrects Regulation Supplementing Solvency II Directive

    EC published the EU Delegated Regulation 2020/442, which corrects the EU Delegated Regulation 2015/35 that supplements Solvency II Directive (2009/138/EC).

    March 26, 2020 WebPage Regulatory News
    News

    FED and FFIEC Offer Reporting Relief to Institutions Due to COVID-19

    FED and FFIEC announced regulatory reporting relief to financial institutions due to disruptions caused by the COVID-19.

    March 26, 2020 WebPage Regulatory News
    RESULTS 1 - 10 OF 4900