nep-rmg New Economics Papers
on Risk Management
Issue of 2017‒11‒05
sixteen papers chosen by
Stan Miles
Thompson Rivers University

  1. The two faces of interbank correlation By Schaeck, Klaus; Silva Buston, Consuelo; Wagner, Wolf
  2. Modified Sharpe Ratios in Real Estate Performance Measurement: Beyond the Standard Cornish Fisher Expansion By Charles-Olivier Amédée-Manesme; Fabrice Barthélémy; Jean-Luc Prigent; Donald Keenan; Mahdi Mokrane
  3. Regulatory Learning: how to supervise machine learning models? An application to credit scoring By Dominique Guegan; Bertrand Hassani
  4. Coming together to address systemic risks: examples of collaboration: remarks at Risk USA 2017 Conference, New York City By Davis, Jeanmarie
  5. Why Does Idiosyncratic Risk Increase with Market Risk? By Söhnke M. Bartram; Gregory Brown; René M. Stulz
  6. Computation of the Corrected Cornish-Fisher Expansion using the Response Surface Methodology: Application to V aR and CV aR By Charles-Olivier Amédée-Manesme; Fabrice Barthélémy; Didier Maillard
  7. Curbing Corporate Debt Bias: Do Limitations to Interest Deductibility Work? By Ruud A. de Mooij; Shafik Hebous
  8. Calibration of Machine Learning Classifiers for Probability of Default Modelling By Pedro G. Fonseca; Hugo D. Lopes
  9. Retail credit scoring using fine-grained payment data By TOBBACK, Ellen; MARTENS, David
  10. Optimal Capital Regulation By Josef Schroth; Stephane Moyen
  11. How Do Banks and Households Manage Interest Rate Risk? Evidence from the Swiss Mortgage Market By Christoph Basten; Benjamin Guin; Cathérine Tahmee Koch
  12. IAS 19 valuations for DB Schemes – true or fair? By Bridget McNally
  13. A Dynamic Measure of Intentional Herd Behavior in Financial Markets By Park, Beum-Jo; Kim, Myung-Joong
  14. The Elephant in the Room: the Impact of Labor Obligations on Credit Markets By Xiaoji Lin; Xiaofei Zhao; Jack Favilukis
  15. A quantitative analysis of risk premia in the corporate bond market By Sara Cecchetti
  16. Efficient Policy Learning By Susan Athey; Stefan Wager

  1. By: Schaeck, Klaus; Silva Buston, Consuelo; Wagner, Wolf
    Abstract: Correlations of stock returns across banks are an essential input into systemic risk measures. We demonstrate that such correlations can be decomposed into two parts: a systematic component arising from diversification activities, and a systemic component specific to banks. We find that at U.S. Banking Holding Companies correlations are to a large extent driven by the systematic component. However, applying the decomposition to the Marginal Expected Shortfall (MES), we show that it is the systemic component that predicts bank failure and risk during the Global Financial Crisis. The results suggest that it is important to distinguish between the two sources of correlations when measuring systemic risk at banks.
    Date: 2017–10
  2. By: Charles-Olivier Amédée-Manesme; Fabrice Barthélémy; Jean-Luc Prigent; Donald Keenan; Mahdi Mokrane (CEMOTEV, Université de Versailles Saint-Quentin-en-Yvelines, France)
    Abstract: An important component in the analysis of real estate performance and allocation is the efficient calibration of the distribution of returns. The classical method is to compute market or sub-market returns and volatilities, and to then calculate the standard performance measure, namely the Sharpe ratio. This measure is only based on the first two moments of the return distribution. Therefore, a significant weakness of this method is that it implicitly assumes that this distribution is Gaussian (if not, the approach may lead to a bad fit for the distribution). In fact, risk comes not only from volatility but from higher moments of the distribution, such as skewness and kurtosis. In order to resolve this issue, we focus on another risk-adjusted performance measure, one that takes the Value-at-Risk (VaR) as the risk measure, as was adopted by the Basel II regulation directive. This criterion is based on specific quantiles of the distribution of returns. When the VaR is computed from the Cornish Fisher expansion, the corresponding risk-adjusted performance measure is called the modified Sharpe ratio. Usually, its computation is based on the first four moments of the return’s distribution. However, this methodology can exhibit several pitfalls, and thus, this paper shows how to make proper use of this tool. The usefulness of the proposed methodology is illustrated through an empirical application to optimal portfolio allocation in commercial real estate, using the IPD database. We find that markets that appear more desirable using simple Sharpe ratios bear, in reality, higher risk when the distribution of returns is taken into account in a more appropriate manner. Institutional investors may find that the technique proposed here is useful in that it allows them to consider non-normality in real estate performance analysis.
    Keywords: Real estate portfolio; performance measures; Cornish Fisher expansion; modified Sharpe ratio
    JEL: C61 G11 R39
    Date: 2017
  3. By: Dominique Guegan (Centre d'Economie de la Sorbonne and LabEx ReFi); Bertrand Hassani (Group Capgemini and Centre d'Economie de la Sorbonne and LabEx ReFi)
    Abstract: The arrival of big data strategies is threatening the lastest trends in financial regulation related to the simplification of models and the enhancement of the comparability of approaches chosen by financial institutions. Indeed, the intrinsic dynamic philosophy of Big Data strategies is almost incompatible with the current legal and regulatory framework as illustrated in this paper. Besides, as presented in our application to credit scoring, the model selection may also evolve dynamically forcing both practitioners and regulators to develop libraries of models, strategies allowing to switch from one to the other as well as supervising approaches allowing financial institutions to innovate in a risk mitigated environment. The purpose of this paper is therefore to analyse the issues related to the Big Data environment and in particular to machine learning models highlighting the issues present in the current framework confronting the data flows, the model selection process and the necessity to generate appropriate outcomes.
    Keywords: Big Data; Credit scoring; machine learning; AUC; regulation
    Date: 2017–07
  4. By: Davis, Jeanmarie (Federal Reserve Bank of New York)
    Abstract: Remarks at Risk USA 2017 Conference, New York City.
    Keywords: collaboration; T+2 initiative; Securities Industry and Financial Markets Association (SIFMA); central counterparties (or CCPs); margin rules; OTC derivative markets; coordination; collateral support agreements; cybersecurity; Financial Services Information Sharing and Analysis Center (FS-ISAC); Sheltered Harbor initiative
    Date: 2017–10–26
  5. By: Söhnke M. Bartram; Gregory Brown; René M. Stulz
    Abstract: From 1963 through 2015, idiosyncratic risk (IR) is high when market risk (MR) is high. We show that the positive relation between IR and MR is highly stable through time and is robust across exchanges, firm size, liquidity, and market-to-book groupings. Though stock liquidity affects the strength of the relation, it is strong for the most liquid stocks. The relation has roots in fundamentals. Higher market risk predicts greater idiosyncratic earnings volatility as well as dispersion and errors in analysts’ earnings forecasts. Firm characteristics related to the ability of firms to adjust to higher uncertainty help explain the strength of the relation. We find evidence that the relation is weaker for firms with more growth options, which is con-sistent with the view that such options provide a hedge against macroeconomic uncertainty.
    Keywords: uncertainty, idiosyncratic risk, market risk, growth options, liquidity, limits to arbitrage
    JEL: G10 G11 G12
    Date: 2017
  6. By: Charles-Olivier Amédée-Manesme; Fabrice Barthélémy; Didier Maillard (CEMOTEV, Université de Versailles Saint-Quentin-en-Yvelines, France)
    Abstract: The Cornish-Fisher expansion is a simple way to determine quantiles of non- normal distributions. It is frequently used by practitioners and by academics in risk mana- gement, portfolio allocation, and asset liability management. It allows us to consider non- normality and, thus, moments higher than the second moment, using a formula in which terms in higher-order moments appear explicitly. This paper has two primary objectives. First, we resolve the classic confusion between the skewness and kurtosis coefficients of the formula and the actual skewness and kurtosis of the distribution when using the Cornish{ Fisher expansion. Second, we use the response surface approach to estimate a function for these two values. This helps to overcome the difficulties associated with using the Cornish{ Fisher expansion correctly to compute value at risk (V aR). In particular, it allows a direct computation of the quantiles. Our methodology has many practical applications in risk ma- nagement and asset allocation.
    Keywords: Cornish-Fisher Expansion, Response Surface Methodology, Quantiles, Value at Risk, Expected Shortfall
    JEL: C15 C44 C46 D81 G32
    Date: 2017
  7. By: Ruud A. de Mooij; Shafik Hebous
    Abstract: Tax provisions favoring corporate debt over equity finance (“debt bias†) are widely recognized as a risk to financial stability. This paper explores whether and how thin-capitalization rules, which restrict interest deductibility beyond a certain amount, affect corporate debt ratios and mitigate financial stability risk. We find that rules targeted at related party borrowing (the majority of today’s rules) have no significant impact on debt bias—which relates to third-party borrowing. Also, these rules have no effect on broader indicators of firm financial distress. Rules applying to all debt, in contrast, turn out to be effective: the presence of such a rule reduces the debt-asset ratio in an average company by 5 percentage points; and they reduce the probability for a firm to be in financial distress by 5 percent. Debt ratios are found to be more responsive to thin capitalization rules in industries characterized by a high share of tangible assets.
    Keywords: corporate tax, capital structure, debt bias, thin capitalization rule
    JEL: G32 H25
    Date: 2017
  8. By: Pedro G. Fonseca; Hugo D. Lopes
    Abstract: Binary classification is highly used in credit scoring in the estimation of probability of default. The validation of such predictive models is based both on rank ability, and also on calibration (i.e. how accurately the probabilities output by the model map to the observed probabilities). In this study we cover the current best practices regarding calibration for binary classification, and explore how different approaches yield different results on real world credit scoring data. The limitations of evaluating credit scoring models using only rank ability metrics are explored. A benchmark is run on 18 real world datasets, and results compared. The calibration techniques used are Platt Scaling and Isotonic Regression. Also, different machine learning models are used: Logistic Regression, Random Forest Classifiers, and Gradient Boosting Classifiers. Results show that when the dataset is treated as a time series, the use of re-calibration with Isotonic Regression is able to improve the long term calibration better than the alternative methods. Using re-calibration, the non-parametric models are able to outperform the Logistic Regression on Brier Score Loss.
    Date: 2017–10
  9. By: TOBBACK, Ellen; MARTENS, David
    Abstract: In this big data era, banks (like any other large company) are looking for novel ways to leverage their existing data assets. A major data source that has not been used to the full extent yet, is the massive fine-grained payment data on their customers. In this paper, a design is proposed that builds predictive credit scoring models using the fine-grained payment data. Using a real-life data set of 183 million transactions made by 2.6 million customers, we show that our proposed design adds complementary predictive power to the current credit scoring models. Such improvement has a big impact on the overall working of the bank, from applicant scoring to minimum capital requirements.
    Date: 2017–10
  10. By: Josef Schroth (Bank of Canada); Stephane Moyen (Deutsche Bundesbank)
    Abstract: We study constrained-efficient bank capital regulation in a model with market-imposed equity requirements. Banks hold equity buffers to insure against sudden loss of funding access. However, bank equity is privately costly in the model such that banks choose only partial self-insurance. Equity requirements are occasionally binding as a result. Constrained-efficient regulation requires banks to build up additional equity buffers and compensates them for the cost of equity with a permanent increase in lending margins. When buffers are depleted regulation relaxes market-imposed equity requirements by raising bank future prospects via temporarily elevated lending margins.
    Date: 2017
  11. By: Christoph Basten; Benjamin Guin; Cathérine Tahmee Koch
    Abstract: We exploit a unique data set that features both un-intermediated mortgage requests and independent offers from multiple banks for each request. We show that households typically are not prudent risk managers but prioritize the minimization of current mortgage payments over the risk of possible hikes in future mortgage payments. We also provide evidence that banks do influence the contracted mortgage rate fixation periods, trading off their own exposure to interest rate risk against the borrowers’ affordability and credit risk. Our results challenge the implicit assumption of the existing mortgage choice literature whereby fixation periods are determined entirely by households.
    Keywords: Fixed-Rate Mortgage (FRM), Adjustable-Rate Mortgage (ARM), fixation period, maturity mismatch, interest rate risk, credit risk, duration
    JEL: D12 E43 G21
    Date: 2017
  12. By: Bridget McNally (Department of Economics, Finance and Accounting, Maynooth University.)
    Abstract: Purpose - This paper argues that the accounting standards’ requirement for pension scheme liabilities to be discounted by reference to market yields at the end of the reporting period on high quality corporate bonds, potentially produces an artificial result which is at odds with the “fair representation” objective of these standards. Design/methodology/approach –The approach is a theoretical analysis of the relevant reporting standards with the use of a theoretical example to demonstrate the impact where trustees adopt a hedged approach to portfolio investment. Findings - Where the fund has adopted a hedging strategy and has invested in “risk – free” assets, the term, quantity and duration/maturity of which, is intended to match the term quantity and maturity of the scheme liabilities, applying the requirements potentially results in the reporting in sponsoring company financial statements of fluctuating surpluses or deficits each year which are potentially ill-informed and misleading. Originality/value – Pension scheme surpluses or deficits reported in the financial statements of listed companies are potentially very significant numbers, however the dangers posed by theoretical nature of the calculation has largely gone unreported.
    Date: 2017
  13. By: Park, Beum-Jo; Kim, Myung-Joong
    Abstract: This paper suggests a dynamic measure of intentional herding, causing the excess volatility or even systemic risk in financial markets, which is based on a new concept of cumulative returns in the same direction as well as the collective behavior of all investors towards the market consensus. Differing from existing measures, the measure allows us to directly detect time-varying and market-wide intentional herding using the model of Dynamic Conditional Correlation (DCC) (Engle, 2002) between the financial market and its components that is partially free of spurious herding due to the inclusion of the variables of the number of economic news announcements as a proxy of market information. Strong evidence in favor of the dynamic measure over the other measures is based on empirical application in the U.S. markets (DJIA and S&P100), supporting the tendency to exhibit time-varying intentional herding. Much more important is a finding that the impact of intentional herding on market volatility tends to be stronger during the periods of turbulent markets like the degradation of U.S. sovereign credit rating by S&P, and be more significant in S&P 100 than DJIA.
    Keywords: Intentional herd behavior, Dynamic conditional correlation, News announcements, Dynamic measure, Herding tests, Volatility, Quantile regression
    JEL: C10 G0 G02
    Date: 2017–10–01
  14. By: Xiaoji Lin (Ohio State University); Xiaofei Zhao (University of Texas-Dallas); Jack Favilukis (University of British Columbia)
    Abstract: We show that labor market frictions are first-order for understanding credit markets. Wage growth and labor share forecast aggregate credit spreads and debt growth as well as or better than alternative predictors. They also predict credit risk and debt growth in a cross-section of international firms. Finally, high labor share firms choose lower financial leverage. A model with labor market frictions and risky long-term debt can explain these findings, and produce large credit spreads despite realistically low default probabilities. This is because pre-committed payments to labor make other committed payments (i.e. interest) riskier.
    Date: 2017
  15. By: Sara Cecchetti (Bank of Italy)
    Abstract: We propose an econometric model to decompose corporate bond spreads into compensation required by investors for unpredictable future changes in the credit environment and for expected default losses. We use the model to understand whether the significant reduction in corporate bond spreads observed since the launch of the CSPP (Corporate Sector Purchase Programme) is attributable more to the fact that expansionary monetary policy measures tend to increase the risk appetite of investors and compress risk premia, or to the ability of unconventional measures to reduce expected default losses by improving investors’ expectations about the economic and financial conditions of issuers.
    Keywords: bond excess return, credit default swap, distress risk premium, expected default frequancy, jump-at-default risk premium
    JEL: B26 C02 F30 G12 G15
    Date: 2017–10
  16. By: Susan Athey; Stefan Wager
    Abstract: We consider the problem of using observational data to learn treatment assignment policies that satisfy certain constraints specified by a practitioner, such as budget, fairness, or functional form constraints. This problem has previously been studied in economics, statistics, and computer science, and several regret-consistent methods have been proposed. However, several key analytical components are missing, including a characterization of optimal methods for policy learning, and sharp bounds for minimax regret. In this paper, we derive lower bounds for the minimax regret of policy learning under constraints, and propose a method that attains this bound asymptotically up to a constant factor. Whenever the class of policies under consideration has a bounded Vapnik-Chervonenkis dimension, we show that the problem of minimax-regret policy learning can be asymptotically reduced to first efficiently evaluating how much each candidate policy improves over a randomized baseline, and then maximizing this value estimate. Our analysis relies on uniform generalizations of classical semiparametric efficiency results for average treatment effect estimation, paired with sharp concentration bounds for weighted empirical risk minimization that may be of independent interest.
    Date: 2017–02

This nep-rmg issue is ©2017 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.