nep-rmg New Economics Papers
on Risk Management
Issue of 2022‒10‒24
eighteen papers chosen by

  1. Learning Value-at-Risk and Expected Shortfall By D Barrera; S Crépey; E Gobet; Hoang-Dung Nguyen; B Saadeddine
  2. Investment in Disaster Risk Management in Europe Makes Economic Sense By World Bank
  3. Persistence and Volatility Spillovers of Bitcoin price to Gold and Silver prices By Yaya, OlaOluwa A; Lukman, Adewale F.; Vo, Xuan Vinh
  4. Modeling and Pricing Cyber Insurance -- A Survey By Kerstin Awiszus; Thomas Knispel; Irina Penner; Gregor Svindland; Alexander Vo{\ss}; Stefan Weber
  5. What drives the risk of European banks during crises? New evidence and insights By Ion Lapteacru
  6. Anomaly Detection on Financial Time Series by Principal Component Analysis and Neural Networks By Stéphane Crépey; Lehdili Noureddine; Nisrine Madhar; Maud Thomas
  7. Portfolio Risk Assessment Using Risk Index By World Bank
  8. The effect of structural risks on financial downturns By Hodula, Martin; Pfeifer, Lukáš; Janků, Jan
  9. Risk information - normal markets and the COVID-19 pandemic period By Srivastava, Pranjal; Jacob, Joshy
  10. Interpretable Selective Learning in Credit Risk By Dangxing Chen; Weicheng Ye; Jiahui Ye
  11. External Wealth of Nations and Systemic Risk By Alin Marius Andries; Alexandra-Maria Chiper; Steven Ongena; Nicu Sprincean
  12. The Limits to Local Insurance By Johannes Gierlinger; Pau Milán
  13. Physics-Informed Convolutional Transformer for Predicting Volatility Surface By Soohan Kim; Seok-Bae Yun; Hyeong-Ohk Bae; Muhyun Lee; Youngjoon Hong
  14. Monotonic Neural Additive Models: Pursuing Regulated Machine Learning Models for Credit Scoring By Dangxing Chen; Weicheng Ye
  15. How many inner simulations to compute conditional expectations with least-square Monte Carlo? By Aurélien Alfonsi; Bernard Lapeyre; Jérôme Lelong
  16. The impact of risk cycles on business cycles: a historical view By Jón Daníelsson; Marcela Valenzuela; Ilknur Zer
  17. Time-variation between metal commodities and oil, and the impact of oil shocks: GARCH-MIDAS and DCC-MIDAS analyses By Yaya, OlaOluwa S.; Ogbonna, Ahamuefula E.; Adesina, Ayobami O.; Alobaloke, Kafayat; Vo, Xuan Vinh
  18. Sovereign Risk, Financial Fragility and Debt Maturity By Dallal Bendjellal

  1. By: D Barrera (UNIANDES - Universidad de los Andes [Bogota]); S Crépey (LPSM (UMR_8001) - Laboratoire de Probabilités, Statistique et Modélisation - SU - Sorbonne Université - CNRS - Centre National de la Recherche Scientifique - UPCité - Université Paris Cité, UPCité - Université Paris Cité); E Gobet (CMAP - Centre de Mathématiques Appliquées - Ecole Polytechnique - X - École polytechnique - CNRS - Centre National de la Recherche Scientifique, X - École polytechnique, Université Paris-Saclay); Hoang-Dung Nguyen (LPSM (UMR_8001) - Laboratoire de Probabilités, Statistique et Modélisation - SU - Sorbonne Université - CNRS - Centre National de la Recherche Scientifique - UPCité - Université Paris Cité, UPCité - Université Paris Cité, Natixis); B Saadeddine (UPS - Université d'Évry Paris-Saclay, Crédit Agricole)
    Abstract: We propose a non-asymptotic convergence analysis of a two-step approach to learn a conditional value-at-risk (VaR) and expected shortfall (ES) in a nonparametric setting using Rademacher and Vapnik-Chervonenkis bounds. Our approach for the VaR is extended to the problem of learning at once multiple VaRs corresponding to different quantile levels. This results in efficient learning schemes based on neural network quantile and least-squares regressions. An a posteriori Monte Carlo (non-nested) procedure is introduced to estimate distances to the ground-truth VaR and ES without access to the latter. This is illustrated using numerical experiments in a Gaussian toy-model and a financial case-study where the objective is to learn a dynamic initial margin.
    Keywords: value-at-risk,expected shortfall,quantile regression,quantile crossings,neural networks,62L20,62M45,91G60,91G70,2G32
    Date: 2022–09–13
  2. By: World Bank
    Keywords: Conflict and Development - Disaster Management Environment - Natural Disasters Urban Development - Hazard Risk Management
    Date: 2021–06
  3. By: Yaya, OlaOluwa A; Lukman, Adewale F.; Vo, Xuan Vinh
    Abstract: The paper investigated persistence, returns and volatility spill overs from the Bitcoin market to Gold and Silver markets using daily datasets from 2 January 2018 to 31 July 2020. We applied the fractional persistence framework to the price series, returns and volatility proxy series. The results showed that price persistence with Bitcoin posed the highest volatility, while Silver posed the lowest volatility. The results of multivariate GARCH modelling, using the CCC-VARMA-GARCH model and other lower variants indicated the impossibility of returns spill over between Bitcoin and Gold (or Silver) market, while there existed volatility spill overs and these were bi-directional in form of shocks and volatility transmissions. Appropriate portfolio management and hedging strategies rendered towards the end of the paper required more gold and silver investments in the portfolio of Bitcoin to fully have the diversification advantage and reduce risk to the minimum without reducing the portfolio return expectancy.
    Keywords: Bitcoin; Commodity markets; CCC-VARMA-GARCH model; Volatility spill overs; Portfolio management
    JEL: C22
    Date: 2022–09–09
  4. By: Kerstin Awiszus; Thomas Knispel; Irina Penner; Gregor Svindland; Alexander Vo{\ss}; Stefan Weber
    Abstract: The paper provides a comprehensive overview of modeling and pricing cyber insurance and includes clear and easily understandable explanations of the underlying mathematical concepts. We distinguish three main types of cyber risks: idiosyncratic, systematic, and systemic cyber risks. While for idiosyncratic and systematic cyber risks, classical actuarial and financial mathematics appear to be well-suited, systemic cyber risks require more sophisticated approaches that capture both network and strategic interactions. In the context of pricing cyber insurance contracts, interdependence issues arise for both systematic and systemic cyber risks; classical actuarial valuation must be expanded to include more complex methodologies, e.g., concepts of risk-neutral valuation and (set-valued) monetary risk measures.
    Date: 2022–08
  5. By: Ion Lapteacru (BSE - Bordeaux Sciences Economiques - UB - Université de Bordeaux - CNRS - Centre National de la Recherche Scientifique)
    Abstract: Based on an extensive dataset of 1,156 European banks over the 1995-2015 period, we aim to provide new insights on the determinants of European banks' risk-taking during crisis events, employing a novel asymmetric Z-score. Our results suggest that more capital, lower ratios of loans to deposits and of liquid assets to total assets and lower share of non-deposit and short-term funding in total funding are associated with lower bank risk and this relationship is stronger during the crises. Moreover, having low costs compared to their revenues reduces the risk of European banks in normal times and has the same impact during the crises. Being involved in non-interest-generating activities makes banks riskier. Finally, being large and having higher net interest margin make banks more stable, but this positive effect is diminished for the size and vanished for the profitability during crisis times. And some differences are observed between Western and Eastern European countries.
    Keywords: European banking,bank risk,financial crisis,Z-score. JEL: G21
    Date: 2022–09–12
  6. By: Stéphane Crépey (LPSM (UMR_8001) - Laboratoire de Probabilités, Statistique et Modélisation - SU - Sorbonne Université - CNRS - Centre National de la Recherche Scientifique - UPCité - Université Paris Cité, UPCité - Université Paris Cité); Lehdili Noureddine (Natixis); Nisrine Madhar (LPSM (UMR_8001) - Laboratoire de Probabilités, Statistique et Modélisation - SU - Sorbonne Université - CNRS - Centre National de la Recherche Scientifique - UPCité - Université Paris Cité, UPCité - Université Paris Cité, Natixis); Maud Thomas (LPSM (UMR_8001) - Laboratoire de Probabilités, Statistique et Modélisation - SU - Sorbonne Université - CNRS - Centre National de la Recherche Scientifique - UPCité - Université Paris Cité, SU - Sorbonne Université)
    Abstract: We consider time series representing a wide variety of risk factors in the context of financial risk management. A major issue of these data is the presence of anomalies that induce a miscalibration of the models used to quantify and manage risk, whence potentially erroneous risk measures on their basis. Therefore, the detection of anomalies is of utmost importance in financial risk management. We propose an approach that aims at improving anomaly detection on financial time series, overcoming most of the inherent difficulties. One first concern is to extract from the time series valuable features that ease the anomaly detection task. This step is ensured through a compression and reconstruction of the data with the application of principal component analysis. We define an anomaly score using a feed-forward neural network. A time series is deemed contaminated when its anomaly score exceeds a given cutoff. This cutoff value is not a hand-set parameter, instead it is calibrated as a parameter of the neural network throughout the minimisation of a customized loss function. The efficiency of the proposed model with respect to several well-known anomaly detection algorithms is numerically demonstrated. We show on a practical case of value-at-risk estimation, that the estimation errors are reduced when the proposed anomaly detection model is used, together with a naive imputation approach to correct the anomaly.
    Keywords: anomaly detection,financial time series,principal component analysis,neural network,density estimation,missing data,market risk,value at risk
    Date: 2022–09–15
  7. By: World Bank
    Keywords: Energy - Hydro Power Environment - Environmental Protection Environment - Water Resources Management Water Resources - Dams and Reservoirs
    Date: 2021–04
  8. By: Hodula, Martin; Pfeifer, Lukáš; Janků, Jan
    Abstract: We investigate the extent to which various structural risks exacerbate the materialization of cyclical risk. We use a large database covering all sorts of cyclical and structural features of the financial sector and the real economy for a panel of 30 countries over the period 2006Q1–2019Q4. We show that elevated levels of structural risks may have an important role in explaining the severity of cyclical and credit risk materialization during financial cycle contractions. Among these risks, private and public sector indebtedness, banking sector resilience and concentration of real estate exposures stand out. Moreover, we show that the elevated levels of some of the structural risks identified may be related to long-standing accommodative economic policy. Our evidence implies a stronger role for macroprudential policy, especially in countries with higher levels of structural risks. JEL Classification: E32, G15, G21, G28
    Keywords: cyclical risk, event study, financial cycle, panel regression, structural risks, systemic risk
    Date: 2022–09
  9. By: Srivastava, Pranjal; Jacob, Joshy
    Abstract: The paper investigates how the market infers changes in the firm-level discount rate (risk information) in normal and turbulent times. The study focuses on two key sources of risk information, earnings announcements of firms and changes in the market risk premium. We employ a recently proposed measure that limits the impact of event risk while estimating the forward-looking risk information from option prices. We find that both earnings announcements and the changes in market risk impact firm-level discount rates, but both sources exhibit a significant time variation. The impact of market risk changes is lower in favorable conditions and higher during crisis periods. Using COVID19 as an exogenous shock, we show that the influence of earnings announcements becomes insignificant during a crisis. The results suggest lower attention to firm-specific risk factors in times of a systemic crisis, in contrast to normal times.
    Date: 2022–10–06
  10. By: Dangxing Chen; Weicheng Ye; Jiahui Ye
    Abstract: The forecasting of the credit default risk has been an important research field for several decades. Traditionally, logistic regression has been widely recognized as a solution due to its accuracy and interpretability. As a recent trend, researchers tend to use more complex and advanced machine learning methods to improve the accuracy of the prediction. Although certain non-linear machine learning methods have better predictive power, they are often considered to lack interpretability by financial regulators. Thus, they have not been widely applied in credit risk assessment. We introduce a neural network with the selective option to increase interpretability by distinguishing whether the datasets can be explained by the linear models or not. We find that, for most of the datasets, logistic regression will be sufficient, with reasonable accuracy; meanwhile, for some specific data portions, a shallow neural network model leads to much better accuracy without significantly sacrificing the interpretability.
    Date: 2022–09
  11. By: Alin Marius Andries (Alexandru Ioan Cuza University of Iasi; Romanian Academy - Institute for Economic Forecasting); Alexandra-Maria Chiper (Alexandru Ioan Cuza University of Iasi); Steven Ongena (University of Zurich - Department of Banking and Finance; Swiss Finance Institute; KU Leuven; NTNU Business School; Centre for Economic Policy Research (CEPR)); Nicu Sprincean (Alexandru Ioan Cuza University of Iasi)
    Abstract: External imbalances played a pivotal role in the run-up to the global financial crisis, being an important underlying cause of the ensuing turmoil. While current account (flow) imbalances have narrowed in the aftermath of the crisis, net international investment position (stock) imbalances still persist. In this paper, we explore the implications of countries’ net foreign positions on systemic risk. Using a sample composed of 450 banks located in 46 advanced, developing and emerging countries over the period 2000-2020, we document that banks can reduce their systemic risk exposure when the countries where they are incorporated maintain creditor positions vis-à-vis the rest of the world. However, only the equity components of the net international investment positions are responsible for this outcome, whereas debt flows do not contribute significantly. In addition, we find that the heterogeneity across countries is substantial and that only banks located in advanced markets that maintain their creditor positions have the potential to improve their resilience to system-wide shocks. Our findings are relevant for policy makers who seek to improve banks’ resilience to adverse shocks and to maintain financial stability.
    Keywords: External Wealth of Nations, External Imbalances, Net International Investment Position, Systemic Risk, Financial Stability
    JEL: F32 G21 G32
    Date: 2022–09
  12. By: Johannes Gierlinger; Pau Milán
    Abstract: We study decentralized insurance when multiple risks are payoff-relevant, but each agent may only trade a (possibly different) subset of risks. Unless (at least) one agent can trade every risk, insurance markets remain incomplete, and the economy is not resilient to worst-case events. We also identify spill overs in any feasible allocation: others’ inability to trade some risks restricts an agent’s resilience to joint realizations. Unless an agent can trade a superset of i’s risks, agent i is not resilient to them. In an application, we model constraints as risk-sharing networks and measure resilience in a Malawian village.
    Keywords: risk sharing, incomplete markets, market insurance, Networks
    JEL: D11 D52 D53 D85 G52
    Date: 2021–10
  13. By: Soohan Kim; Seok-Bae Yun; Hyeong-Ohk Bae; Muhyun Lee; Youngjoon Hong
    Abstract: Predicting volatility is important for asset predicting, option pricing and hedging strategies because it cannot be directly observed in the financial market. The Black-Scholes option pricing model is one of the most widely used models by market participants. Notwithstanding, the Black-Scholes model is based on heavily criticized theoretical premises, one of which is the constant volatility assumption. The dynamics of the volatility surface is difficult to estimate. In this paper, we establish a novel architecture based on physics-informed neural networks and convolutional transformers. The performance of the new architecture is directly compared to other well-known deep-learning architectures, such as standard physics-informed neural networks, convolutional long-short term memory (ConvLSTM), and self-attention ConvLSTM. Numerical evidence indicates that the proposed physics-informed convolutional transformer network achieves a superior performance than other methods.
    Date: 2022–09
  14. By: Dangxing Chen; Weicheng Ye
    Abstract: The forecasting of credit default risk has been an active research field for several decades. Historically, logistic regression has been used as a major tool due to its compliance with regulatory requirements: transparency, explainability, and fairness. In recent years, researchers have increasingly used complex and advanced machine learning methods to improve prediction accuracy. Even though a machine learning method could potentially improve the model accuracy, it complicates simple logistic regression, deteriorates explainability, and often violates fairness. In the absence of compliance with regulatory requirements, even highly accurate machine learning methods are unlikely to be accepted by companies for credit scoring. In this paper, we introduce a novel class of monotonic neural additive models, which meet regulatory requirements by simplifying neural network architecture and enforcing monotonicity. By utilizing the special architectural features of the neural additive model, the monotonic neural additive model penalizes monotonicity violations effectively. Consequently, the computational cost of training a monotonic neural additive model is similar to that of training a neural additive model, as a free lunch. We demonstrate through empirical results that our new model is as accurate as black-box fully-connected neural networks, providing a highly accurate and regulated machine learning method.
    Date: 2022–09
  15. By: Aurélien Alfonsi (MATHRISK - Mathematical Risk Handling - UPEM - Université Paris-Est Marne-la-Vallée - ENPC - École des Ponts ParisTech - Inria de Paris - Inria - Institut National de Recherche en Informatique et en Automatique, CERMICS - Centre d'Enseignement et de Recherche en Mathématiques et Calcul Scientifique - ENPC - École des Ponts ParisTech); Bernard Lapeyre (MATHRISK - Mathematical Risk Handling - UPEM - Université Paris-Est Marne-la-Vallée - ENPC - École des Ponts ParisTech - Inria de Paris - Inria - Institut National de Recherche en Informatique et en Automatique, CERMICS - Centre d'Enseignement et de Recherche en Mathématiques et Calcul Scientifique - ENPC - École des Ponts ParisTech); Jérôme Lelong (DAO - Données, Apprentissage et Optimisation - LJK - Laboratoire Jean Kuntzmann - Inria - Institut National de Recherche en Informatique et en Automatique - CNRS - Centre National de la Recherche Scientifique - UGA - Université Grenoble Alpes - Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology - UGA - Université Grenoble Alpes)
    Abstract: The problem of computing the conditional expectation E[f (Y)|X] with least-square Monte-Carlo is of general importance and has been widely studied. To solve this problem, it is usually assumed that one has as many samples of Y as of X. However, when samples are generated by computer simulation and the conditional law of Y given X can be simulated, it may be relevant to sample K ∈ N values of Y for each sample of X. The present work determines the optimal value of K for a given computational budget, as well as a way to estimate it. The main take away message is that the computational gain can be all the more important that the computational cost of sampling Y given X is small with respect to the computational cost of sampling X. Numerical illustrations on the optimal choice of K and on the computational gain are given on different examples including one inspired by risk management.
    Keywords: Least square Monte-Carlo,Conditional expectation estimators,Variance reduction
    Date: 2022–09–08
  16. By: Jón Daníelsson; Marcela Valenzuela; Ilknur Zer
    Abstract: We investigate the effects of financial risk cycles on business cycles, using a panel spanning 73 countries since 1900. Agents use a Bayesian learning model to form their beliefs on risk. We construct a proxy of these beliefs and show that perceived low risk encourages risk-taking, augmenting growth at the cost of accumulating financial vulnerabilities, and therefore, a reversal in growth follows. The reversal is particularly pronounced when the low-risk environment persists and credit growth is excessive. Global-risk cycles have a stronger effect on growth than local-risk cycles via their impact on capital flows, investment, and debt-issuer quality.
    Keywords: Stock market volatility; Uncertainty; Monetary policy independence; Financial instability; Risk-taking; Global financial cycles
    JEL: F30 F44 G15 G18 N10 N20
    Date: 2022–09–09
  17. By: Yaya, OlaOluwa S.; Ogbonna, Ahamuefula E.; Adesina, Ayobami O.; Alobaloke, Kafayat; Vo, Xuan Vinh
    Abstract: Extant literature establishes co-movements among commodity (metal and oil) prices; whereas oil price/shocks aggregate, as a lone predictor, has relative predictability for most financial assets. We assess the predictability of Baumeister and Hamilton's (2019) decomposed oil shocks (economic activity shocks, oil consumption demand shocks, oil inventory demand shocks, and oil supply shocks) for conditional volatilities of prominently traded precious metals (gold, palladium, platinum, and silver) using GARCH-MIDAS-X framework. The asymmetric effect of decomposed oil shocks on precious metals’ volatilities is examined. The DCC-MIDAS framework allows to investigate the conditional correlations and volatility between oil and precious metal prices. Results show that precious metals exhibit hedging potentials against oil demand and supply shocks, with heterogeneity observed in the precious metal-oil shocks nexus. Asymmetry is evident in the responses of metals’ volatility to oil shocks. DCC-MIDAS results reveal significant dynamic correlations between oil prices and precious metals (except for platinum). Our results are robust (sensitive) to precious metals (oil shocks) proxies. The findings are insightful for commodity market stakeholders.
    Keywords: GARCH-MIDAS; DCC-MIDAS; Disaggregated oil shocks; Dynamic correlation; Platinum
    JEL: C22
    Date: 2022–09–23
  18. By: Dallal Bendjellal (Aix Marseille Univ, CNRS, AMSE, Marseille, France.)
    Abstract: This paper studies the transmission of a sovereign debt crisis in which a shift in default risk generates a recession and gives rise to a doom loop between sovereign distress and bank fragility with important amplification effects. The model is used to investigate the macroeconomic and welfare effects of altering debt maturity during the crisis. Short-term maturities alleviate the bankers' losses on long-term bonds and moderate the recession at the cost of higher levels of debt in the future. In contrast, long-term maturities are more effective to reduce the households' welfare losses as they lower default risk and distortionary taxes.
    Keywords: debt crisis, sovereign default risk, financial fragility, maturity dynamics
    JEL: E44 E62 H12
    Date: 2022–09

General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.