nep-rmg New Economics Papers
on Risk Management
Issue of 2021‒03‒01
seventeen papers chosen by
Stan Miles
Thompson Rivers University

  1. Probability of Default (PD) Model to Estimate Ex Ante Credit Risk By Anna Burova; Henry Penikas; Svetlana Popova
  2. Bank Regulatory Reforms and Declining Diversity of Bank Credit Allocation By Takeo Hoshi; Ke Wang
  3. Asset allocation in extreme market conditions: a comparative analysis between developed and emerging economies By Montshioa, Keitumetse; Muteba Mwamba, John Weirstrass; Bonga-Bonga, Lumengo
  4. Cybersecurity Risk By Chris Florakis; Christodoulos Louca; Roni Michaely; Michael Weber
  5. Multivariate higher order moments in multi-state life insurance By Jamaal Ahmad
  6. Incorporating Financial Big Data in Small Portfolio Risk Analysis: Market Risk Management Approach By Donggyu Kim; Seunghyeon Yu
  7. Deep Stochastic Volatility Model By Xiuqin Xu; Ying Chen
  8. Momentum Has Its Own Values By Hongwei Chuang
  9. Equity portfolio diversification: how many stocks are enough? Evidence from India By Raju, Rajan; Agarwalla, Sobhesh Kumar
  10. On the interaction between monetary and macroprudential policies By Martin, Alberto; Mendicino, Caterina; Van der Ghote, Alejandro
  11. Parameter uncertainty in policy planning models: Using portfolio management methods to choose optimal policies under world market volatility By Mukashov, Askar
  12. Efficient mean-variance portfolio selection by double regularization By N'Golo Kone
  13. Management of Multiple Sources of Risk in Livestock Production By McKendree, Melissa G. S.; Tonsor, Glynn T.; Schulz, Lee L.
  14. Network Based Evidence of the Financial Impact of Covid-19 Pandemic By Daniel Felix Ahelegbey; Paola Cerchiello; Roberta Scaramozzino
  15. The Economic Consequences of Bankruptcy Reform By Tal Gross; Raymond Kluender; Feng Liu; Matthew J. Notowidigdo; Jialan Wang
  16. Optimal Dynamic Futures Portfolios Under a Multiscale Central Tendency Ornstein-Uhlenbeck Model By Tim Leung; Yang Zhou
  17. What can credit vintages tell us about non-performing loans? By Santiago Gamba-Santamaria; Luis Fernando Melo-Velandia; Camilo Orozco-Vanegas

  1. By: Anna Burova (Bank of Russia, Russian Federation); Henry Penikas (Bank of Russia, Russian Federation); Svetlana Popova (Bank of Russia, Russian Federation)
    Abstract: A genuine measure of an ex ante credit risk links borrowers’ financial position with the odds of default. Comprehension of borrower’s financial position is proxied by the derivatives of its filled financial statements, i.e. financial ratios. To measure an ex ante credit risk, one needs a forward-looking estimate. We identify statistically significant relationships between the shortlisted financial ratios and the subsequent default events. To estimate the odds of the borrower to default on its obligations, we simulate its probability of default at a horizon of one year. We horse run the constructed PD model against the alternative measures of ex ante credit risk that the related literature on bank risk-taking widely uses: credit quality groups and credit spreads in interest rates. We compare the results obtained with the PD model, and with the alternative approaches. We find that the PD model predicts the default event more accurately at a horizon of one year. We conclude that the developed measure of ex ante credit risk is feasible for estimating the risk-taking behaviour by banks and analysing the shifts in portfolio composition with the sufficient degree of granularity. The model could be used in applied research as the tool for measuring ex ante credit risk based on micro level data (credit registry).
    Keywords: ex ante probability of default, corporate credit, credit registry, probability of default mode, credit quality groups, credit spreads
    JEL: E44 E51 E52 E58 G21 G28
    Date: 2020–12
  2. By: Takeo Hoshi (The University of Tokyo); Ke Wang (Federal Reserve Board)
    Abstract: This paper addresses the concerns on correlated risks across banks that tightening regulation may have induced. Facing higher required capital ratio after the global financial crisis, a bank can reduce the risk-weighted assets by shifting its portfolios from asset classes with high risk-weights to asset classes with low risk-weights. This may reduce the risk exposures of individual banks, but may end up concentrating various banks’ assets to the same set of low risk assets, hence increase the joint default probability and systemic risk of the banking system. Using risk-weighted asset data in Form FFIEC101, reported by the U.S. banks that are allowed to use the advanced approach, we show banks’ average risk weights indeed declined since 2010, partly due to portfolio shifts in credit allocation. We measure the convergence in credit allocation by the cosine similarity of portfolio compositions for pairs of banks. We document that the average cosine similarity across the advanced approach banks rose monotonically and significantly since 2010, which coincides with a period of tightened capital regulations. Finally, we observe that the two prevailing systemic risk measures –SRISK and CoVaR –also show signs of convergence among banks during the same time period. We conclude that the capital regulation may have unintended consequences on systemic risk by encouraging herd behavior across regulated banks.
    Date: 2021–02
  3. By: Montshioa, Keitumetse; Muteba Mwamba, John Weirstrass; Bonga-Bonga, Lumengo
    Abstract: This study makes use of the Extreme Value Theory, based on the Generalised Pareto Distribution and the Generalised Extreme Value Distribution, to construct efficient portfolios during periods of turmoil. The portfolios are constructed by combining different assets constituted by their positions in emerging and developed stock markets, with the aim of identifying which assets combinations provide optimal portfolio allocations during turmoil periods. For the developed stock markets, the study uses the French CAC 40, the Canadian S&P/TSX, the United Kingdom FTSE 100, the Japanese NIKKEI 225 and the United States S&P500 indices and returns. Five emerging stock markets indices are used, namely, the Brazilian BOVESPA, the Chinese SHCOMP the Indian S&P BSE SENEX, Indonesian JSI and the Turkish BIST 100. The data sample spans from August 1997 to August 2019 and include major economic and financial crises. Our findings show that for the different portfolios constructed, the estimated shape, location, and scale parameters differ depending on the Extreme Value Theory distribution under investigation. Moreover, based on the Generalised Pareto Distribution and the Generalised Extreme Value Distribution for portfolio optimisation, the results of the study show that during extreme conditions investors are prone to allocate more weight to developed stock market assets than to emerging markets. This confirms that developed economies are safe havens, especially during extreme market conditions. Moreover, the GPD is superior as it provides maximum risk-reward ratios.
    Keywords: asset allocation, extreme value, developing economies, emerging markets
    JEL: C51 G11 G15
    Date: 2021–02–23
  4. By: Chris Florakis (University of Liverpool - Management School); Christodoulos Louca (Cyprus University of Technology - Department of Commerce, Finance and Shipping); Roni Michaely (University of Geneva - Geneva Finance Research Institute); Michael Weber (University of Chicago - Booth School of Business; NBER)
    Abstract: We develop a novel firm-level measure of cybersecurity risk using textual analysis of cybersecurity-risk disclosures in corporate filings. The measure successfully identifies firms extensively discussing cybersecurity risk in their 10-K, displays intuitive relations with quantitative measures of cybersecurity risk disclosure language, exhibits a positive trend over time, is more prevalent among industries relying more on information technology systems, correlates with several characteristics linked to firms hit by cyber attacks and, importantly, predicts future cyber attacks. Stocks with high exposure to cybersecurity risk exhibit high expected returns on average, but they perform poorly in periods of increasing attention to cybersecurity risk.
    JEL: G14 G31
    Date: 2020
  5. By: Jamaal Ahmad
    Abstract: It is well-known that combining life annuities and death benefits introduce opposite effects in payments with respect to the unsystematic mortality risk on the lifetime of the insured. In a general multi-state framework with multiple product types, such joint effects are less trivial. In this paper, we consider a multivariate payment process in multi-state life insurance, where the components are defined in terms of the same Markovian state process. The multivariate present value of future payments is introduced, and we derive differential equations and product integral representations of its conditional moments and moment generating function. Special attention is given to pair-wise covariances between two present values, where results closely connected to Hattendorff type of results for the variance are derived. Numerical examples are shown in a disability model and a spouse model to illustrate applicability of the results on insurance of a single life as well as two dependent lives.
    Date: 2021–02
  6. By: Donggyu Kim; Seunghyeon Yu
    Abstract: When applying Value at Risk (VaR) procedures to specific positions or portfolios, we often focus on developing procedures only for the specific assets in the portfolio. However, since this small portfolio risk analysis ignores information from assets outside the target portfolio, there may be significant information loss. In this paper, we develop a dynamic process to incorporate the ignored information. We also study how to overcome the curse of dimensionality and discuss where and when benefits occur from a large number of assets, which is called the blessing of dimensionality. We find empirical support for the proposed method.
    Date: 2021–02
  7. By: Xiuqin Xu; Ying Chen
    Abstract: Volatility for financial assets returns can be used to gauge the risk for financial market. We propose a deep stochastic volatility model (DSVM) based on the framework of deep latent variable models. It uses flexible deep learning models to automatically detect the dependence of the future volatility on past returns, past volatilities and the stochastic noise, and thus provides a flexible volatility model without the need to manually select features. We develop a scalable inference and learning algorithm based on variational inference. In real data analysis, the DSVM outperforms several popular alternative volatility models. In addition, the predicted volatility of the DSVM provides a more reliable risk measure that can better reflex the risk in the financial market, reaching more quickly to a higher level when the market becomes more risky and to a lower level when the market is more stable, compared with the commonly used GARCH type model with a huge data set on the U.S. stock market.
    Date: 2021–02
  8. By: Hongwei Chuang (IUJ Research Institutey, International University of University)
    Abstract: We find high momentum stocks with preserving substantial "fundamental value" are more likely to rebound after unexpected financial shocks. The portfolio test show that our proposed investment strategy can inherit more portfolio downside risk, especially the momentum crash during turbulent times.
    Keywords: Momentum; Financial Crisis; Fama-French Factors; Systemic Risk
    JEL: G11 G12 G14
    Date: 2021–02
  9. By: Raju, Rajan; Agarwalla, Sobhesh Kumar
    Abstract: How many stocks are required to reduce unsystematic risk significantly is an important question for investors. While there is a large body of research on the subject in the United States, there is little formal work on this question in India. We show that a 15-20 stock portfolio, the traditional market rule-of-thumb for a diversified portfolio, is likely inadequate to minimise unsystematic risk. We show that an investor could target to reduce diversifiable risk by 90% with a 90% confidence with a portfolio of 40-50 stocks. We build a practical framework that serves as a baseline for investors to target a specific reduction in diversifiable unsystematic risk at a chosen confidence level.
    Date: 2021–02–23
  10. By: Martin, Alberto; Mendicino, Caterina; Van der Ghote, Alejandro
    Abstract: The Global Financial Crisis fostered the design and adoption of macroprudential policies throughout the world. This raises important questions for monetary policy. What, if any, is the relationship between monetary and macroprudential policies? In particular, how does the effectiveness of macroprudential policies (or lack thereof) influence the conduct of monetary policy? This discussion paper builds on the insights of recent theoretical and empirical research to address these questions. JEL Classification: E3, E44, G01, G21
    Keywords: capital requirements, financial frictions, systemic risk
    Date: 2021–02
  11. By: Mukashov, Askar
    Abstract: This paper suggests using portfolio management methods in policy planning models as a practical tool for determining optimal policy under model parameter uncertainty. We suggest that in addition to calculating the standard policy return estimates, policy options should also be analyzed from the risk perspective by using metrics that inform the effect of parameter uncertainty on policy impact variation. We demonstrate the approach in a Computable General Equilibrium model that analyzes pro-poor agricultural value chains in Senegal under world market uncertainty. We show that prioritizing the rice sector is the most effective policy in terms of expected policy return, but this policy is also associated with the highest risk, leading to an increase in poverty under unfavorable yet realistic scenarios. Much like diversified portfolios in finance, mixed policies that assume the rice sector's promotion combined with other sectors such as milk, vegetables, oilseeds, or fishery, can offer risk reduction at the cost of reduced expected policy return.
    Keywords: policy analysis,CGE modeling,portfolio management,pro-poor growth
    JEL: D58 C68 O13 Q11 I3 O21 G11
    Date: 2021
  12. By: N'Golo Kone
    Abstract: This paper addresses the estimation issue that exists when estimating the traditional mean-variance portfolio. More precisely, the efficient mean-variance is estimated by a double regularization. These regularization techniques namely the ridge, the spectral cut-off, and Landweber-Fridman involve a regularization parameter or penalty term whose optimal value needs to be selected efficiently. A data-driven method has been proposed to select the tuning parameter. We show that the double regularized portfolio guarantees to investors the maximum expected return with the lowest risk. In empirical and Monte Carlo experiments, our double regularized rules are compared to several strategies, such as the traditional regularized portfolios, the new Lasso strategy of Ao et al. (2019), and the naive 1/N strategy in terms of in-sample and out-of-sample Sharpe ratio performance, and it is shown that our method yields significant Sharpe ratio improvements and a reduction in the expected utility loss.
    Keywords: Portfolio selection, efficient mean-variance analysis, double regularization
    JEL: C52 C58 G11
    Date: 2021–02
  13. By: McKendree, Melissa G. S.; Tonsor, Glynn T.; Schulz, Lee L.
    Abstract: Firm operators continually manage multiple sources of risk. In an application to cattle feedlot operations, our objective is to determine if producers view output price and animal health risks separately or jointly. We conduct a survey with a choice experiment placing operators in forward looking, decision-making scenarios, and capture information on past risk management approaches. Evidence regarding a relationship between animal health and output price risk mitigation is mixed and depends on the decision being made. Combined, these results provide new insight into how managers approach multiple risks when facing resource constraints.
    Date: 2021–01–01
  14. By: Daniel Felix Ahelegbey (University of Pavia); Paola Cerchiello (University of Pavia); Roberta Scaramozzino (University of Pavia)
    Abstract: How much the largest worldwide companies, belonging to different sectors of the economy, are suffering from the pandemic? Are economic relations among them changing? In this paper, we address such issues by analysing the top 50 S&P companies by means of market and textual data. Our work proposes a network analysis model that combines such two types of information to highlight the connections among companies with the purpose of investigating the relationships before and during the pandemic crisis. In doing so, we leverage a large amount of textual data through the employment of a sentiment score which is coupled with standard market data. Our results show that the COVID-19 pandemic has largely affected the US productive system, however differently sector by sector and with more impact during the second wave compared to the first.
    Keywords: COVID-19 Pandemic, Textual analysis, Financial risk, Network model
    Date: 2021–02
  15. By: Tal Gross (Boston University;NBER); Raymond Kluender (Harvard University - Harvard Business School); Feng Liu (Consumer Financial Protection Bureau); Matthew J. Notowidigdo (University of Chicago - Booth School of Business; NBER); Jialan Wang (University of Illinois at Urbana-Champaign)
    Abstract: A more generous consumer bankruptcy system provides greater insurance against financial risks but may also raise the cost of credit. We study this trade-off using the 2005 Bankruptcy Abuse Prevention and Consumer Protection Act (BAPCPA), which increased the costs of filing for bankruptcy. We identify the effects of BAPCPA on borrowing costs using variation in the effects of the reform across credit scores. We find that a one-percentage-point reduction in bankruptcy-filing risk decreased credit-card interest rates by 70{90 basis points. Conversely, BAPCPA reduced the insurance value of bankruptcy, with uninsured hospitalizations 70 percent less likely to obtain bankruptcy relief after the reform.
    Date: 2020
  16. By: Tim Leung; Yang Zhou
    Abstract: We study the problem of dynamically trading multiple futures whose underlying asset price follows a multiscale central tendency Ornstein-Uhlenbeck (MCTOU) model. Under this model, we derive the closed-form no-arbitrage prices for the futures contracts. Applying a utility maximization approach, we solve for the optimal trading strategies under different portfolio configurations by examining the associated system of Hamilton-Jacobi-Bellman (HJB) equations. The optimal strategies depend on not only the parameters of the underlying asset price process but also the risk premia embedded in the futures prices. Numerical examples are provided to illustrate the investor's optimal positions and optimal wealth over time.
    Date: 2021–02
  17. By: Santiago Gamba-Santamaria; Luis Fernando Melo-Velandia; Camilo Orozco-Vanegas
    Abstract: Using Colombian credit vintage data, we decompose the non-performing loans into one component that captures the evolution of the payment capacity of borrowers, and other component that captures changes in the credit risk taken by the financial system at the time of loan disbursement. We use intrinsic estimators and penalized regression techniques to overcome the perfect multicollinearity problem that the model entails. We find that these two type of components have evolved differently over time, and that good economic conditions and loose financial conditions improve the payment capacity of borrowers to meet their obligations, and in turn, they tend to coincide with the financial system engaging in riskier loans. Finally, we advocate the use of this methodology as a policy tool that is easy to apply by financial and economic authorities that dispose of a constant flow of credit vintage information. Through it, they will be able to identify the origin of the credit risk materialization and curb the risk taken by the financial system. **** RESUMEN: Usando información de cosechas de crédito, en este documento descomponemos la cartera en mora en un componente que captura la evolución de la capacidad de pago de los deudores y otro componente que captura los cambios en la toma de riesgo de crédito del sistema financiero al momento del desembolso. Utilizamos estimadores intrínsecos y técnicas de regresión penalizadas para solucionar el problema de multicolinealidad perfecta asociado a la estimación de los parámetros de los modelos. Encontramos que estos dos tipos de componentes han evolucionado de manera diferente a lo largo del tiempo y que buenas condiciones económicas y condiciones financieras laxas mejoran la capacidad de pago de los deudores para cumplir con sus obligaciones y, a su vez, tienden a coincidir con el otorgamiento de préstamos de mayor riesgo por parte del sistema financiero. Finalmente, recomendamos el uso de esta metodología como herramienta de política de fácil aplicación por parte de las autoridades financieras y económicas que disponen de un flujo constante de información de cosechas de crédito. A través de ella las autoridades podrían identificar el origen de la materialización del riesgo crediticio y contener la toma de riesgo del sistema financiero.
    Keywords: Cosechas de crédito, cartera en mora, regresiones penalizadas, estimadores intrínsecos, credit vintages, non-performing loans, elastic net regressions, intrinsic estimators.
    JEL: C13 C20 G21
    Date: 2021–02

This nep-rmg issue is ©2021 by Stan Miles. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
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.