Featured Product

    BoE Paper on Machine Learning Approach to Predict Financial Crisis

    January 03, 2020

    BoE published a working paper that details the early warning models developed for financial crisis prediction using machine learning techniques on macro-financial data for 17 countries over 1870–2016. The paper shows that machine learning models mostly outperform logistic regression in out‑of‑sample predictions and forecasting. Due to their greater flexibility, machine learning models have the advantage that they may uncover important non-linear relationships and variable interactions, which may be difficult to identify using classical techniques. The results help policy makers to identify the risk of financial crises in advance and potentially act on these signals.

    The paper describes the dataset and reviews literature on the variables that the authors choose as predictors. It then presents the benchmark logistic regression, outlines the methodology, and provides a brief description of the different machine learning models applied and the Shapley value framework. Next, the paper compares the predictive performance of all models and investigates the importance of the predictors using Shapley values. Finally, the paper looks at the robustness of indicators in a macro-prudential policy context and investigates in detail the role of the yield curve. 

    This paper shows that machine learning models outperform logistic regression in predicting financial crises on a macroeconomic data set covering 17 countries between 1870 and 2016 in both out-of-sample cross-validation and recursive forecasting. The gains in predictive accuracy justify the use of initially more opaque machine learning models. All models consistently identify similar predictors for financial crises, although there are some variations across time reflecting changes in the nature of the global monetary and financial system. While the crucial role of credit is an established result in the literature, the predictive power of the yield curve has obtained far less attention as an early warning indicator. The authors also inspect non-linearities and interactions identified by the machine learning models. Global credit shows a particularly strong non-linearity—only very high global credit growth beyond a certain point influences the prediction of the models. Interactions are particularly strong between global and domestic indicators.

    Overall, the findings suggest a combination of low risk perception, search-for-yield behavior, and strong credit growth in the years preceding a crisis. The results highlight the potential value of machine learning models for broader economic policy making in two key dimensions. First, the approach illustrates how machine learning techniques can uncover important non-linearities and interactions that facilitate superior out-of-sample prediction and forecasting even in situations characterized by relatively small data sets with limited observations of the event of interest. Second, the novel Shapley value approach demonstrates how the black box concern linked to the practical policy application of machine learning models may be overcome. By providing a mechanism to identify the key economic drivers of the predictions generated by such models, the approach allows insights from machine learning models to be integrated into a broader decision making framework while preserving the transparency and accountability of any resulting public policy decision.

     

    Related Link: Working Paper

     

    Keywords: Europe, UK, Banking, Machine Learning, Yield Curve, Financial Stability, Dataset, Research, Early Warning Model, Fintech, BoE

    Related Articles
    News

    BoE Seeks Information Before Migrating Statistical Reporting to BEEDS

    The Bank of England (BoE) published the Statistical Notice 2021/09 requiring additional information from firms and software vendors to assist in the onboarding and testing phases for migrating statistical reporting to the BEEDS portal.

    October 25, 2021 WebPage Regulatory News
    News

    FCA Publishes Final Rules on Investment Firms Prudential Regime

    The Financial Conduct Authority (FCA) published the final rules on the Investment Firms Prudential Regime (IFPR) to streamline and simplify the prudential requirements for solo-regulated UK firms authorized under the Markets in Financial Instruments Directive (MiFID).

    October 25, 2021 WebPage Regulatory News
    News

    CFRF Publishes Guides to Manage Financial Risks from Climate Change

    The working groups of the Climate Financial Risk Forum (CFRF) published a second round of guides (or Session 2 guides), written by the industry for the industry, to help financial firms manage climate-related financial risks.

    October 21, 2021 WebPage Regulatory News
    News

    PRA Finalizes Policy for Non-Performing Exposure Securitizations

    The Prudential Regulation Authority (PRA) published the final Policy Statement PS24/21 that contains the new Non-Performing Exposures Securitization Part of the PRA Rulebook and an updated Supervisory Statement SS10/18 on the general requirements and capital framework with respect to securitizations.

    October 21, 2021 WebPage Regulatory News
    News

    EBA Updates Filing Rules for Supervisory Reporting

    The European Banking Authority (EBA) published version 5.1 of the filing rules for supervisory reporting.

    October 19, 2021 WebPage Regulatory News
    News

    ECB Amends Guideline on Procedures for Collection of AnaCredit Data

    The European Central Bank (ECB) Guideline 2021/1829 on the procedures for the collection of granular credit and credit risk data has been published in the Official Journal of European Union.

    October 19, 2021 WebPage Regulatory News
    News

    ECB Amends Guideline on Procedures for Collection of AnaCredit Data

    The European Central Bank (ECB) Guideline 2021/1829 on the procedures for the collection of granular credit and credit risk data has been published in the Official Journal of European Union.

    October 19, 2021 WebPage Regulatory News
    News

    EBA Publishes Standards on Disclosure of Investment Policy Under IFR

    The European Banking Authority (EBA) published the final draft regulatory technical standards on disclosure of investment policy by investment firms, under the Investment Firms Regulation (IFR).

    October 19, 2021 WebPage Regulatory News
    News

    EU to Explore Potential of Establishing a Joint Cyber Unit

    The European Council adopted conclusions inviting the European Union (EU) and the member states to further develop the cybersecurity crisis management framework.

    October 19, 2021 WebPage Regulatory News
    News

    EC Sets Out Work Program for 2022

    The European Commission (EC) adopted the work program for 2022.

    October 19, 2021 WebPage Regulatory News
    RESULTS 1 - 10 OF 7598