nep-rmg New Economics Papers
on Risk Management
Issue of 2021‒11‒15
seventeen papers chosen by
Stan Miles
Thompson Rivers University

  1. Understanding corporate default using Random Forest: The role of accounting and market information By Alessandro Bitetto; Stefano Filomeni; Michele Modina
  2. Financial Variables as Predictors of Real Growth Vulnerability By Lucrezia Reichlin; Giovanni Ricco; Thomas Hasenzagl
  3. Decrease of capital guarantees in life insurance products: can reinsurance stop it? By Marcos Escobar-Anel; Yevhen Havrylenko; Michel Kschonnek; Rudi Zagst
  4. A Meta-Method for Portfolio Management Using Machine Learning for Adaptive Strategy Selection By Damian Kisiel; Denise Gorse
  5. The Limits of Model-Based Regulation By Behn, Markus; Haselmann, Rainer; Vig, Vikrant
  6. The Case for a Normatively Charged Approach to Regulating Shadow Banking - Multipolar Regulatory Dialogues as a Means to Detect Tail Risks and Preclude Regulatory Arbitrage By Thiemann, Matthias; Tröger, Tobias
  7. Why Do Bank Boards Have Risk Committees? By Stulz, Rene M.; Tompkins, James G.; Williamson, Rohan; Ye, Zhongxia Shelly
  8. Cyber Risk Frequency, Severity and Insurance Viability By Matteo Malavasi; Gareth W. Peters; Pavel V. Shevchenko; Stefan Tr\"uck; Jiwook Jang; Georgy Sofronov
  9. Оценка качества ссудного портфеля по данным на уровне займа // Assessing the quality of loan portfolio based on the loan level data By Конурбаева Наталья // Konurbayeva Natalya; Нурханова Оксана // Nurkhanova Oxana; Хакимжанов Сабит // Khakimzhanov Sabit
  10. Data-driven Hedging of Stock Index Options via Deep Learning By Jie Chen; Lingfei Li
  11. THE MORE THE BETTER? INFORMATION SHARING AND CREDIT RISK By Irina Iakimenko; Maria Semenova; Eugeny Zimin
  12. Multiplicative Component GARCH Model of Intraday Volatility By Xiufeng Yan
  13. The start-up decision under default risk By Nicola Comincioli; Paolo M. Panteghini; Sergio Vergalli
  14. Home Bias in Sovereign Exposure and the Probability of Bank Default – Evidence From EU-Stress Test Data By Meyland, Dominik; Schäfer, Dorothea
  15. Dynamic Interdependence and Volatility Transmission from the American to the Brazilian Stock Market By Edson Z. Monte; Lucas B. Defanti
  16. Does regulation only bite the less profitable? Evidence from the too-big-to-fail reforms By Goel, Tirupam; Lewrick, Ulf; Mathur, Aakriti
  17. Examining the liquidity risk in the household sector and the policy implications By Kim, Young Il

  1. By: Alessandro Bitetto (University of Pavia); Stefano Filomeni (University of Essex); Michele Modina (University of Molise)
    Abstract: Recent evidence highlights the importance of hybrid credit scoring models to evaluate borrowers’ creditworthiness. However, the current hybrid models neglect to consider the role of public-peer market information in addition to accounting information on default prediction. This paper aims to fill this gap in the literature by providing novel evidence on the impact of market information in predicting corporate defaults for unlisted firms. We employ a sample of 10,136 Italian micro-, small-, and mid-sized enterprises (MSMEs) that borrow from 113 cooperative banks from 2012–2014 to examine whether market pricing of public firms adds additional information to accounting measures in predicting default of private firms. Specifically, we estimate the probability of default (PD) of MSMEs using equity price of size-and industry- matched public firms, and then we adopt advanced statistical techniques based on parametric algorithm (Multivariate Adaptive Regression Spline) and non-parametric machine learning model (Random Forest). Moreover, by using Shapley values, we assess the relevance of market information in predicting corporate credit risk. Firstly, we show the predictive power of Merton’s PD on default prediction for unlisted firms. Secondly, we show the increased predictive power of credit risk models that consider both the Merton’s PD and accounting information to assess corporate credit risk. We trust the results of this paper contribute to the current debate on safeguarding the continuity and the resilience of the banking sector. Indeed, banks’ hybrid credit scoring methodologies that also embed market information prove to be successful to assess credit risk of unlisted firms and could be useful for forward-looking financial risk management frameworks
    Keywords: Default Risk, Distance to Default, Machine Learning, Merton model, SME, PD, SHAP, Autoencoder, Random Forest, XAI
    JEL: C52 C53 D82 D83 G21 G22
    Date: 2021–10
  2. By: Lucrezia Reichlin (London Business School); Giovanni Ricco (OFCE - Observatoire français des conjonctures économiques - Sciences Po - Sciences Po); Thomas Hasenzagl
    Abstract: We evaluate the role of financial conditions as predictors of macroeconomic risk first in the quantile regression framework of Adrian et al. (2019b), which allows for non-linearities, and then in a novel linear semi-structural model as proposed by Hasenzagl et al. (2018). We distinguish between price variables such as credit spreads and stock variables such as leverage. We find that (i) although the spreads correlate with the left tail of the conditional distribution of GDP growth, they provide limited advanced information on growth vulnerability; (ii) nonfinancial leverage provides a leading signal for the left quantile of the GDP growth distribution in the 2008 recession; (iii) measures of excess leverage conceptually similar to the Basel gap, but cleaned from business cycle dynamics via the lenses of the semi-structural model, point to two peaks of accumulation of risks – the eighties and the first eight years of the new millennium, with an unstable relationship with business cycle chronology.
    Keywords: Financial cycle,Business cycle,Credit,Financial crises,Downside risk,Entropy,Quantile regressions
    Date: 2020–01–01
  3. By: Marcos Escobar-Anel; Yevhen Havrylenko; Michel Kschonnek; Rudi Zagst
    Abstract: We analyze the potential of reinsurance for reversing the current trend of decreasing capital guarantees in life insurance products. Providing an insurer with an opportunity to shift part of the financial risk to a reinsurer, we solve the insurer's dynamic investment-reinsurance optimization problem under simultaneous Value-at-Risk and no-short-selling constraints. We introduce the concept of guarantee-equivalent utility gain and use it to compare life insurance products with and without reinsurance. Our numerical studies indicate that the optimally managed reinsurance allows the insurer to offer significantly higher capital guarantees to clients without any loss in the insurer's expected utility. The longer the investment horizon and the less risk-averse the insurer, the more prominent the reinsurance benefit.
    Date: 2021–11
  4. By: Damian Kisiel; Denise Gorse
    Abstract: This work proposes a novel portfolio management technique, the Meta Portfolio Method (MPM), inspired by the successes of meta approaches in the field of bioinformatics and elsewhere. The MPM uses XGBoost to learn how to switch between two risk-based portfolio allocation strategies, the Hierarchical Risk Parity (HRP) and more classical Na\"ive Risk Parity (NRP). It is demonstrated that the MPM is able to successfully take advantage of the best characteristics of each strategy (the NRP's fast growth during market uptrends, and the HRP's protection against drawdowns during market turmoil). As a result, the MPM is shown to possess an excellent out-of-sample risk-reward profile, as measured by the Sharpe ratio, and in addition offers a high degree of interpretability of its asset allocation decisions.
    Date: 2021–11
  5. By: Behn, Markus; Haselmann, Rainer; Vig, Vikrant
    Abstract: Using loan-level data from Germany, we investigate how the introduction of model-based capital regulation affected banks' ability to absorb shocks. The objective of this regulation was to enhance financial stability by making capital requirements responsive to asset risk. Our evidence suggests that banks 'optimized' model-based regulation to lower their capital requirements. Banks systematically underreported risk, with under reporting being more pronounced for banks with higher gains from it. Moreover, large banks benefitted from the regulation at the expense of smaller banks. Overall, our results suggest that sophisticated rules may have undesired effects if strategic misbehavior is difficult to detect.
    Keywords: capital regulation,internal ratings,complexity of regulation,Basel regulation
    JEL: G01 G21 G28
    Date: 2021
  6. By: Thiemann, Matthias; Tröger, Tobias
    Abstract: This paper contributes to the debate on the adequate regulatory treatment of non-bank financial intermediation (NBFI). It proposes an avenue for regulators to keep regulatory arbitrage under control and preserve sufficient space for efficient financial innovation at the same time. We argue for a normative approach to supervision that can overcome the proverbial race between hare and hedgehog in financial regulation and demonstrate how such an approach can be implemented in practice. We first show that regulators should primarily analyse the allocation of tail risk inherent in NBFI. Our paper proposes to apply regulatory burdens equivalent to prudential banking regulation if the respective transactional structures become only viable through indirect or direct access to (ad hoc) public backstops. Second, we use insights from the scholarship on regulatory networks as communities of interpretation to demonstrate how regulators can retrieve the information on transactional innovations and their risk-allocating characteristics that they need to make the pivotal determination. We suggest in particular how supervisors should structure their relationships with semi-public gatekeepers such as lawyers, auditors and consultants to keep abreast of the risk-allocating features of evolving transactional structures. Finally, this paper uses the example of credit funds as non-bank entities economically engaged in credit intermediation to illustrate the merits of the proposed normative framework and to highlight that multipolar regulatory dialogues are needed to shed light on the specific risk-allocating characteristics of recent contractual innovations.
    Keywords: shadow banking,regulatory arbitrage,principles-based regulation,credit funds,prudential supervision,non-bank financial intermediation
    JEL: G21 G28 H77 K22 K23 L22
    Date: 2020
  7. By: Stulz, Rene M. (Ohio State University and European Corporate Governance Institute); Tompkins, James G. (Kennesaw State University); Williamson, Rohan (Georgetown University); Ye, Zhongxia Shelly (University of Texas at San Antonio)
    Abstract: We develop a theory of bank board risk committees. With this theory, such committees are valuable even though there is no expectation that bank risk is lower if the bank has a well-functioning risk committee. As predicted by our theory (1) many large and complex banks voluntarily chose to have a risk committee before the Dodd-Frank Act forced bank holding companies with assets in excess of $10 billion to have a board risk committee, and (2) establishing a board risk committee does not reduce a bank’s risk on average. Using unique interview data, we show that the work of risk committees is consistent with our theory in part.
    JEL: G21 G28 G34
    Date: 2021–07
  8. By: Matteo Malavasi (Department of Actuarial Studies and Business Analytics, Macquarie University, Australia); Gareth W. Peters (Department of Statistics and Applied Probability, University of California Santa Barbara, USA; Department of Actuarial Studies and Business Analytics, Macquarie University, Australia); Pavel V. Shevchenko (Department of Actuarial Studies and Business Analytics, Macquarie University, Australia; Center for Econometrics and Business Analytics, St. Petersburg State University, Russia); Stefan Tr\"uck (Department of Actuarial Studies and Business Analytics, Macquarie University, Australia); Jiwook Jang (Department of Actuarial Studies and Business Analytics, Macquarie University, Australia); Georgy Sofronov (Department of Mathematics and Statistics, Macquarie University, Australia)
    Abstract: In this study an exploration of insurance risk transfer is undertaken for the cyber insurance industry in the United States of America, based on the leading industry dataset of cyber events provided by Advisen. We seek to address two core unresolved questions. First, what factors are the most significant covariates that may explain the frequency and severity of cyber loss events and are they heterogeneous over cyber risk categories? Second, is cyber risk insurable in regards to the required premiums, risk pool sizes and how would this decision vary with the insured companies industry sector and size? We address these questions through a combination of regression models based on the class of Generalised Additive Models for Location Shape and Scale (GAMLSS) and a class of ordinal regressions. These models will then form the basis for our analysis of frequency and severity of cyber risk loss processes. We investigate the viability of insurance for cyber risk using a utility modelling framework with premium calculated by classical certainty equivalence analysis utilising the developed regression models. Our results provide several new key insights into the nature of insurability of cyber risk and rigorously address the two insurance questions posed in a real data driven case study analysis.
    Date: 2021–11
  9. By: Конурбаева Наталья // Konurbayeva Natalya (National Bank of Kazakhstan); Нурханова Оксана // Nurkhanova Oxana (National Bank of Kazakhstan); Хакимжанов Сабит // Khakimzhanov Sabit (National Bank of Kazakhstan)
    Abstract: В этой статье проводится анализ источника информации – Кредитный регистр, для оценки портфеля банков на уровне каждого займа (loan level data). В статье вводится понятие дефолта, основанного на косвенных показателях с использованием кредитного регистра. Разрабатываются показатели, которые можно использовать для оценки динамики состояния каждого займа с возможностью агрегирования на уровень заёмщика. Проводится аналитическая оценка, позволяющая выявить рефинансированные займы и «вечнозелёные» займы. Описаны и внедрены категории для распределения займов внутри портфеля с целью своевременного выявления ухудшения состояния займа, позволяющего применять меры раннего реагирования со стороны надзорного органа, а также оценивать кредитный риск на уровне банковской системы. Проведена проверка качества методики на основе имеющихся исторических сведений по передаче портфеля в Фонд проблемных кредитов и признания банком займов с просроченной задолженностью свыше 90 дней перед лишением лицензии, а также оценён объём ложноположительных значений, выявляемых по методике, но в последующем предоставленным в Кредитный регистр с нулевым основным долгом. Представленная методика является первой попыткой применения анализа на основе займа в Казахстане, которую можно развивать с использованием новых расширенных данных по займу и заёмщику, внедрённых в Кредитный регистр с июля 2019 года. Кроме того, следующим этапом после оценки качества портфеля планируется оценка вероятности дефолта заёмщика, а также проведение стресс тестирования. // This Paper analyzes the source of information – the Credit Registry – to assess the portfolio of banks at the level of each loan (loan level data). The Paper introduces the concept of default based on indirect indicators using the Credit Registry. Indicators that can be used to assess the dynamics in the status of each loan with the ability to aggregate at the borrower level are being designed. An analytical assessment is conducted to identify refinanced loans and “evergreen” loans. The categories for the distribution of loans within the portfolio are described and introduced in order to identify the deterioration of loan on a timely basis, allowing the application of early response measures by the supervisor as well as the assessment of credit risk at the banking system’s level. The quality of the methodology was checked on the basis of available historical information about the transfer of the portfolio to the Problem Loans Fund and the recognition by the bank of loans past due more than 90 days before the license was revoked; in addition, the volume of false positives detected by the methodology but subsequently submitted to the Credit Registry with zero main debt was assessed. The presented methodology is the first attempt of applying a loan-based analysis in Kazakhstan that can be developed using the new extended loan and borrower data incorporated into the Credit Registry since July 2019. Besides, the next stage after assessing the quality of portfolio will be the assessment of probability of borrower’s default as well as the stress testing.
    Keywords: кредитный риск, кредитный анализ, вероятность дефолта, кредитный регистр, анализ на уровне займа, рефинансирование, «вечнозелёные» займы, сredit risk, loan review, probability of default, сredit Registry, loan level review, refinancing, "evergreen" loans
    JEL: C81 C83 G21
    Date: 2021
  10. By: Jie Chen; Lingfei Li
    Abstract: We develop deep learning models to learn the hedge ratio for S&P500 index options directly from options data. We compare different combinations of features and show that a feedforward neural network model with time to maturity, Black-Scholes delta and a sentiment variable (VIX for calls and index return for puts) as input features performs the best in the out-of-sample test. This model significantly outperforms the standard hedging practice that uses the Black-Scholes delta and a recent data-driven model. Our results demonstrate the importance of market sentiment for hedging efficiency, a factor previously ignored in developing hedging strategies.
    Date: 2021–11
  11. By: Irina Iakimenko (National Research University Higher School of Economics); Maria Semenova (National Research University Higher School of Economics); Eugeny Zimin (National Research University Higher School of Economics)
    Abstract: Correctly estimating borrower credit risk is a task of particular and growing importance for banks all around the globe. Formal information sharing mechanisms are aimed to reduce information asymmetry in the credit markets and to enhance the precision of those estimates. In the literature, however, whether more, and more detailed, borrower information shared by credit bureaus and credit registries is always associated with higher quality bank credit portfolios and lower credit risk is not completely unambiguous. More credit information disclosed by information intermediaries tends to result in a weaker disciplinary effect of credit history, which means higher credit risk. The accuracy of assessing the creditworthiness of borrowers grows due to an increase in the predictive power of scoring models, which leads to a reduction in credit risk. In this paper, we make a first attempt to examine the nonlinearity of this effect. We study the relationship between the depth of credit information disclosed and the stability of the banking sector in terms of credit risk. Based on data on 80 countries for 2004–2015, we show that the relationship between disclosure and credit risk is non-linear: we observe the lowest levels of credit risk at the minimum and maximum levels of disclosure. We analyze the influence of national institutional quality and financial development on the nature of the relationship. We show that credit risk decreases with increasing amounts of disclosure by credit bureaus and credit registers in well-developed financial markets and in a high-quality institutional environment.
    Keywords: Credit risk, Credit bureau, Credit registry, Bank, Information sharing
    JEL: G21 G28
    Date: 2021
  12. By: Xiufeng Yan
    Abstract: This paper proposes a multiplicative component intraday volatility model. The intraday conditional volatility is expressed as the product of intraday periodic component, intraday stochastic volatility component and daily conditional volatility component. I extend the multiplicative component intraday volatility model of Engle (2012) and Andersen and Bollerslev (1998) by incorporating the durations between consecutive transactions. The model can be applied to both regularly and irregularly spaced returns. I also provide a nonparametric estimation technique of the intraday volatility periodicity. The empirical results suggest the model can successfully capture the interdependency of intraday returns.
    Date: 2021–11
  13. By: Nicola Comincioli (Fondazione Eni Enrico Mattei, Università degli Studi di Brescia); Paolo M. Panteghini (University of Brescia, CESifo); Sergio Vergalli (Fondazione Eni Enrico Mattei, Università degli Studi di Brescia)
    Abstract: This study introduces a real option model to investigate how fiscal policy affects a representative firm's investment decision and to measure its welfare effects. On the one hand, the effects of financial instability on the optimal investment timing and on the probability of default are studied. On the other hand, it is shown how the net present value of an investment project, the tax revenue generated and the welfare are influenced by financial instability. Then, a comparison of welfare effects of tax policy on start-ups, mature and obliged firms is provided. This comparison provides policy-makers a tool to shape their tax systems according to the characteristics of their firms. All presented analyses are supported by numerical simulations, based on realistic data.
    Keywords: Real Options, Business Taxation, Default Risk
    JEL: H25 G33 G38
    Date: 2021–10
  14. By: Meyland, Dominik; Schäfer, Dorothea
    JEL: G21
    Date: 2021
  15. By: Edson Z. Monte; Lucas B. Defanti
    Abstract: The main aim of this paper is to verify the dynamic interdependence and transmission of volatility from the American (SP500) to the Brazilian stock market (IBOVESPA and sectoral indexes). Estimates were performed by GARCH/BEKK methodology, considering the period from January 2007 to December 2019. In the periods considered as “critical events†there was a significant increase in the conditional covariance between SP500 and Brazilian stock indexes (IBOVESPA and sector indices), which suggests for the hypothesis of financial contagion. The covariance increased more intensely and persistently during the so-called subprime crisis, one that had a major impact on the Brazilian economy, especially for the financial and industrial indexes. Furthermore, conditional variance estimates for Brazilian indexes revealed that that internal turmoil, whether economic or political, regardless of the international scenario (“critical events†), affected the volatility of the Brazilian stock market. These results have important implications regarding the future decisions of economic agents (politicians and investors), contributing to a better understanding of the behavior of the Brazilian stock market vis-à -vis the American stock market and the internal turbulences in the Brazilian economy, whether political or economic.
    Keywords: United States; Brazil; Stock Market; Volatility; GARCH-BEKK.
    JEL: G17 C32 C58
    Date: 2021–10–09
  16. By: Goel, Tirupam (Bank for International Settlements); Lewrick, Ulf (Bank for International Settlements); Mathur, Aakriti (Bank of England)
    Abstract: Profitability underpins the opportunity cost of shrinking assets and the ability to generate capital. It thus shapes banks’ responses to higher capital requirements. We present a stylised model to formalise this insight and test our theoretical predictions on a cornerstone of the too-big-to-fail reforms. Leveraging textual analysis to identify the treatment date, we show that less profitable banks reduced their systemic importance as intended by regulation. Those close to the regulatory thresholds that determine bank-specific capital surcharges – a source of exogenous variation in the regulatory treatment – shrunk by even more. In contrast, more profitable banks continued to expand.
    Keywords: Global systemically important bank (G-SIB); textual analysis; capital regulation; systemic risk; bank profitability; difference-in-differences (DD)
    JEL: G21 G28 L51
    Date: 2021–10–29
  17. By: Kim, Young Il
    Abstract: In the wake of an unprecedented health crisis, households who lack liquid assets that could tackle their growing deficit (=income-expenditure) will endure severe financial difficulties. The share of households facing liquidity risk will increase as incomes fall by bigger margins and exposure to the shock intensifies. The liquidity risk resulting from COVID-19 will be even more pronounced among the economically vulnerable; specifically, those in the bottom quintile in terms of income and net assets, and temporary and daily wage workers. Households at liquidity risk are particularly concentrated in the low income quintile. As such, a short-term income support program offering even a small amount of aid (e.g. 1 million won) could greatly help to reduce their liquidity risk. In terms of support for at-liquidity-risk households, a selective approach which focuses the income support on the economically vulnerable and provides credit support in the form of collateral loans to asset-owning households will be more effective in easing the liquidity risk and the government's fiscal burden.
    Date: 2020

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.