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
BCBS is consulting on the principles for operational resilience and the revisions to the principles for sound management of operational risk for banks.
The Financial Stability Institute (FSI) of BIS published a brief note that examines the supervisory challenges associated with certain temporary regulatory relief measures introduced by BCBS and prudential authorities in response to the COVID-19 pandemic.
HKMA, together with the Banking Sector Small and Medium-Size Enterprise (SME) Lending Coordination Mechanism, announced a ninety-day repayment deferment for trade facilities under the Pre-approved Principal Payment Holiday Scheme.
The Advisory Scientific Committee of ESRB published a response, in the form of an Insights Paper, to the EBA proposals for reforms to the stress testing framework in EU.
MAS announced several initiatives to support adoption of the Singapore Overnight Rate Average (SORA), which is administered by MAS.
BoE updated the reporting template for Form ER as well as the Form ER definitions, which contain guidance on the methodology to be used in calculating annualized interest rates.
PRA published the policy statement PS19/20 on the final policy for extending coverage under the Financial Services Compensation Scheme (FSCS) for Temporary High Balance.
EBA published the final draft implementing technical standards for disclosures and reporting on the minimum requirements for own funds and eligible liabilities (MREL) and the total loss-absorbing capacity (TLAC) requirements in EU.
EBA published an erratum for the phase 2 of technical package on the reporting framework 2.10.
EC published the Implementing Regulation 2020/1145, which lays down technical information for calculation of technical provisions and basic own funds.