On the accuracy of alternative approaches for calibrating bank stress test models

Kupiec, Paul H.

doi:10.1016/j.jfs.2018.08.001

Cited by 18 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jagtiani et al 2018 The impact of machine learning in banking supervision in terms of new possible analytical solutions and risks involved in those new approaches. Kupiec et al 2018 Addressing the need for validation of bank stress test models, by emphasising model forecast accuracy. A Lasso model shows the best forecasting capabilities for determining capital requirements in stressful conditions.…”

Section: Broeders Et Al 2018mentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Applied to Banking Supervision a Literature Review

Guerra

Castelli

2021

Risks

View full text Add to dashboard Cite

Machine learning (ML) has revolutionised data analysis over the past decade. Like innumerous other industries heavily reliant on accurate information, banking supervision stands to benefit greatly from this technological advance. The objective of this review is to provide a comprehensive walk-through of how the most common ML techniques have been applied to risk assessment in banking, focusing on a supervisory perspective. We searched Google Scholar, Springer Link, and ScienceDirect databases for articles including the search terms “machine learning” and (“bank” or “banking” or “supervision”). No language, date, or Journal filter was applied. Papers were then screened and selected according to their relevance. The final article base consisted of 41 papers and 2 book chapters, 53% of which were published in the top quartile journals in their field. Results are presented in a timeline according to the publication date and categorised by time slots. Credit risk assessment and stress testing are highlighted topics as well as other risk perspectives, with some references to ML application surveys. The most relevant ML techniques encompass k-nearest neighbours (KNN), support vector machines (SVM), tree-based models, ensembles, boosting techniques, and artificial neural networks (ANN). Recent trends include developing early warning systems (EWS) for bankruptcy and refining stress testing. One limitation of this study is the paucity of contributions using supervisory data, which justifies the need for additional investigation in this field. However, there is increasing evidence that ML techniques can enhance data analysis and decision making in the banking industry.

show abstract

Section: Broeders Et Al 2018mentioning

confidence: 99%

“…Their approach is based on a support vector machine model that helps to define a boundary between solvent and insolvent banks, converting this issue into a classification problem. Kupiec (2018) presents a related study that stresses the need for new methodologies to validate conventional bank stress tests.…”

Section: -2018mentioning

confidence: 99%

Machine Learning Applied to Banking Supervision a Literature Review

Guerra

Castelli

2021

Risks

View full text Add to dashboard Cite

show abstract

“…Several recent papers highlight the importance of stress tests as a supervisory tool and evaluate the costs and benefits of different design choices (see, for example, Lehnert 2015, Schuermann 2014, andreferences therein). Other studies attempt to develop alternative models and approaches to carry out stress tests (see, among others, Acharya, Engle & Pierret 2014, Covas, Rump & Zakrajsek 2014, Kapinos & Mitnik 2016, Kupiec 2018. Recent theoretical contributions focus on how stress tests can affect bank lending (Shapiro & Zeng 2018) and how to develop an optimal disclosure policy for the stress test results (Leitner & Williams 2018).…”

Section: Literature On Stress Testing Modelsmentioning

confidence: 99%

Do stress tests affect bank liquidity creation?

Nguyen

Ahmed

Chevapatrakul

et al. 2020

Journal of Corporate Finance

View full text Add to dashboard Cite

“…Then they use the results to evaluate the numbers reported by individual banks, which include individual banks' future asset-losses, incomes and future capital plans, projected by the banks' own forecast models under the set of forwardlooking economic scenarios; based on the evaluation results, regulators identify those banks which need to replenish their capitals and release such results to the public. However, a recent study by Kupiec (2018), which forecast total incomes (interest incomes plus non-interest incomes) for a representative bank based on regulator-like models, raised serious concerns about the absence of information about how regulators evaluate banks' forecasted numbers and concerns about data overfitting and lack of out-of-sample tests about the forecast accuracies of the stress-test models.…”

Section: Introductionmentioning

confidence: 99%

Bank Net Interest Margin Forecasting and Capital Adequacy Stress Testing by Machine Learning Techniques

Brummelhuis

Luo

2019

SSRN Journal

View full text Add to dashboard Cite

The 2007-09 financial crisis revealed that the investors in the financial market were more concerned about the future as opposed to the current capital adequacies for banks. Stress testing promises to complement the regulatory capital adequacy regimes, which assess a bank's current capital adequacy, with the ability to assess its future capital adequacy based on the projected asset-losses and incomes from the forecasting models from regulators and banks. The effectiveness of stress-test rests on its ability to inform the financial market, which depends on whether or not the market has confidence in the model-projected asset-losses and incomes for banks. Post-crisis studies found that the stress-test results are uninformative and receive insignificant market reactions; others question its validity on the grounds of the poor forecast accuracies using linear regression models which forecast the banking-industry incomes measured by Aggregate Net Interest Margin. Instead, our study focuses on NIM forecasting at an individual bank's level and employs both linear regression and non-linear Machine Learning techniques. First, we present both the linear and non-linear Machine Learning regression techniques used in our study. Then, based on out-of-sample tests and literature-recommended forecasting techniques, we compare the NIM forecast accuracies by 162 models based on 11 different regression techniques, finding that some Machine Learning techniques as well as some linear ones can achieve significantly higher accuracies than the random-walk benchmark, which invalidates the grounds used by the literature to challenge the validity of stress-test. Last, our results from forecast accuracy comparisons are either consistent with or complement those from existing forecasting literature. We believe that the paper is the first systematic study on forecasting bank-specific NIM by Machine Learning Techniques; also, it is a first systematic study on forecast accuracy comparison including both linear and non-linear Machine Learning techniques using financial data for a critical real-world problem; it is a multi-step forecasting example involving iterative forecasting, rolling-origins, recalibration with forecast accuracy measure being scale-independent; robust regression proved to be beneficial for forecasting in presence of outliers. It concludes with policy suggestions and future research directions.

show abstract

On the accuracy of alternative approaches for calibrating bank stress test models

Cited by 18 publications

References 19 publications

Machine Learning Applied to Banking Supervision a Literature Review

Machine Learning Applied to Banking Supervision a Literature Review

Do stress tests affect bank liquidity creation?

Bank Net Interest Margin Forecasting and Capital Adequacy Stress Testing by Machine Learning Techniques

Contact Info

Product

Resources

About