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
Previous ArticleBCB on Innovation Projects Selected for LIFT 2019 Edition
BIS Innovation Hub published the work program for 2021, with focus on suptech and regtech, next-generation financial market infrastructure, central bank digital currencies, open finance, green finance, and cyber security.
In an article published by SRB, Mairead McGuinness, the European Commissioner for Financial Services, Financial Stability, and Capital Markets Union, discussed the progress and next steps toward completion of the Banking Union.
EBA finalized the two sets of draft regulatory technical standards on the identification of material risk-takers and on the classes of instruments used for remuneration under the Investment Firms Directive (IFD).
EC published, in the Official Journal of the European Union, a notification that the European Court of Auditors (ECA) has published a special report on resolution planning in the Single Resolution Mechanism.
BoE published a scenario against which it will be stress testing banks in 2021, in addition to setting out the key elements of the 2021 stress test, guidance on the 2021 stress test, and the variable paths for the 2021 stress test.
PRA published a consultation paper (CP3/21) proposes rules regarding the timing of identity verification required for eligibility of depositor protection under the Financial Services Compensation Scheme (FSCS).
FSB published the work program for 2021, which reflects a strategic shift in priorities in the COVID-19 environment.
FCA announced that 50% firms have started using the new data collection platform RegData, which is slated to replace the existing platform known Gabriel.
Bundesbank published Version 5.0 of the derivation rules for completeness check at the form level, with respect to the data quality of the European harmonized reporting system.
FED finalized a rule that updates capital planning requirements to reflect the new framework from 2019 that sorts large banks into categories, with requirements that are tailored to the risks of each category.