|
on Risk Management |
|
Issue of 2024‒03‒25
fourteen papers chosen by |
| By: | Cathy W. S. Chen; Takaaki Koike; Wei-Hsuan Shau |
| Abstract: | This research incorporates realized volatility and overnight information into risk models, wherein the overnight return often contributes significantly to the total return volatility. Extending a semi-parametric regression model based on asymmetric Laplace distribution, we propose a family of RES-CAViaR-oc models by adding overnight return and realized measures as a nowcasting technique for simultaneously forecasting Value-at-Risk (VaR) and expected shortfall (ES). We utilize Bayesian methods to estimate unknown parameters and forecast VaR and ES jointly for the proposed model family. We also conduct extensive backtests based on joint elicitability of the pair of VaR and ES during the out-of sample period. Our empirical study on four international stock indices confirms that overnight return and realized volatility are vital in tail risk forecasting. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.07134&r=rmg |
| By: | Matthijs Breugem; Raffaele Corvino; Roberto Marfe; Lorenzo Schonleber |
| Abstract: | This paper studies the measurement of forward-looking tail risk in US equity markets around the COVID-19 outbreak. We document that financial markets are informative about how pandemic risk has spread in the economy in advance of the actual outbreak. While the tail risk of the market index did not respond before the outbreak, investors identified less pandemic-resilient economic sectors whose tail risk boomed in advance of both the market drawdown and the implementation of social distancing provisions. This pattern is consistent across different methodologies for measuring forward-looking tail risk, using option contracts, and across various horizons. |
| Keywords: | G01, G10, G12, G14 |
| Date: | 2024 |
| URL: | http://d.repec.org/n?u=RePEc:cca:wpaper:714&r=rmg |
| By: | Suparna Biswas; Rituparna Sen |
| Abstract: | Left truncated and right censored data are encountered frequently in insurance loss data due to deductibles and policy limits. Risk estimation is an important task in insurance as it is a necessary step for determining premiums under various policy terms. Spectral risk measures are inherently coherent and have the benefit of connecting the risk measure to the user's risk aversion. In this paper we study the estimation of spectral risk measure based on left truncated and right censored data. We propose a non parametric estimator of spectral risk measure using the product limit estimator and establish the asymptotic normality for our proposed estimator. We also develop an Edgeworth expansion of our proposed estimator. The bootstrap is employed to approximate the distribution of our proposed estimator and shown to be second order ``accurate''. Monte Carlo studies are conducted to compare the proposed spectral risk measure estimator with the existing parametric and non parametric estimators for left truncated and right censored data. Based on our simulation study we estimate the exponential spectral risk measure for three data sets viz; Norwegian fire claims data set, Spain automobile insurance claims and French marine losses. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.14322&r=rmg |
| By: | Kristy Jansen (University of Southern California and De Nederlandsche Bank); Sven Klingler (BI Norwegian Business School); Angelo Ranaldo (University of St. Gallen; Swiss Finance Institute); Patty Duijm (De Nederlandsche Bank) |
| Abstract: | Pension funds rely on interest rate swaps to hedge the interest rate risk arising from their liabilities. Analyzing unique data on Dutch pension funds, we show that this hedging behavior exposes pension funds to liquidity risk due to margin calls, which can be as large as 15% of their total assets. Our analysis uncovers three key findings: (i) pension funds with tighter regulatory constraints use swaps more aggressively; (ii) in response to rising interest rates, triggering margin calls, pension funds predominantly sell safe and short-term government bonds; (iii) we demonstrate that this procyclical selling adversely affects the prices of these bonds. |
| Keywords: | Pension funds, fixed income, interest rate swaps, liability hedging, liquidity risk, margin calls, price impact |
| JEL: | E43 G12 G18 |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:chf:rpseri:rp2416&r=rmg |
| By: | Andrei Neagu; Fr\'ed\'eric Godin; Clarence Simard; Leila Kosseim |
| Abstract: | Dynamic hedging is the practice of periodically transacting financial instruments to offset the risk caused by an investment or a liability. Dynamic hedging optimization can be framed as a sequential decision problem; thus, Reinforcement Learning (RL) models were recently proposed to tackle this task. However, existing RL works for hedging do not consider market impact caused by the finite liquidity of traded instruments. Integrating such feature can be crucial to achieve optimal performance when hedging options on stocks with limited liquidity. In this paper, we propose a novel general market impact dynamic hedging model based on Deep Reinforcement Learning (DRL) that considers several realistic features such as convex market impacts, and impact persistence through time. The optimal policy obtained from the DRL model is analysed using several option hedging simulations and compared to commonly used procedures such as delta hedging. Results show our DRL model behaves better in contexts of low liquidity by, among others: 1) learning the extent to which portfolio rebalancing actions should be dampened or delayed to avoid high costs, 2) factoring in the impact of features not considered by conventional approaches, such as previous hedging errors through the portfolio value, and the underlying asset's drift (i.e. the magnitude of its expected return). |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.13326&r=rmg |
| By: | Daniel Celeny; Lo\"ic Mar\'echal |
| Abstract: | We extract firms' cyber risk with a machine learning algorithm measuring the proximity between their disclosures and a dedicated cyber corpus. Our approach outperforms dictionary methods, uses full disclosure and not devoted-only sections, and generates a cyber risk measure uncorrelated with other firms' characteristics. We find that a portfolio of US-listed stocks in the high cyber risk quantile generates an excess return of 18.72\% p.a. Moreover, a long-short cyber risk portfolio has a significant and positive risk premium of 6.93\% p.a., robust to all factors' benchmarks. Finally, using a Bayesian asset pricing method, we show that our cyber risk factor is the essential feature that allows any multi-factor model to price the cross-section of stock returns. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.04775&r=rmg |
| By: | Roberto Marfe; Julien Penasse |
| Abstract: | This paper estimates consumption and GDP tail risk dynamics over the long run (1900{ 2020). Our predictive approach circumvents the scarcity of large macroeconomic crises by exploiting a rich information set covering 42 countries. This exible approach does not require asset price information and can thus serve as a benchmark to evaluate the empirical validity of rare disasters models. Our estimates covary with asset prices and forecast future stock returns, in line with theory. A calibration disciplined by our estimates supports the prediction that macroeconomic tail risk drives the equity premium. |
| Keywords: | rare disasters, equity premium, return predictability |
| Date: | 2024 |
| URL: | http://d.repec.org/n?u=RePEc:cca:wpaper:715&r=rmg |
| By: | Knobloch, Ralf |
| Abstract: | Unternehmen sehen sich üblicherweise den unterschiedlichsten operativen und strategischen Risiken ausgesetzt. Daher ist das Risikoportfolio eines Unternehmens aus Sicht des betriebswirtschaftlichen Risikomanagement i.d.R. sehr inhomogen bezüglich der verwendeten Verteilungsmodelle. Neben der Bewertung der Einzelrisiken ist es die Aufgabe des quantitativen Risikomanagements, alle Einzelrisiken in einer Risikokennzahl (z.B. Value at Risk oder Expected Shortfall) zu aggregieren. Dazu werden Szenarien (mit einer Monte-Carlo-Simulation) simuliert, so dass die Verteilung des Gesamtrisikos mit Risikokennzahlen aggregiert und analysiert werden kann. Dabei muss zusätzlich die Abhängigkeitsstruktur der Einzelrisiken modelliert werden. Ein möglicher Ansatz zur Modellierung der Abhängigkeitsstruktur ist die Vorgabe einer Korrelationsmatrix. Der vorliegende Artikel beschäftigt anhand von Beispielen zum einen mit Konzepten und Methoden einer solchen Modellierung und zum anderen mit den Schwierigkeiten, die damit verbunden sind. Es zeigt sich, dass man bei der Wahl einer Korrelationsmatrix verschiedene Einschränkungen zu beachten hat. Ferner kann es zu einer vorgegebenen Korrelationsmatrix mehrere passende gemeinsame Verteilungen der Einzelrisken geben. Dies hat zur Folge, dass die Aggregation der Einzelrisiken in einer Risikokennzahl aus mathematischer Sicht nicht eindeutig ist. |
| Keywords: | Quantitatives Risikomanagement, Value at Risk, Korrelationsmatrix, Risikoaggregation, Fréchet-Hoeffding-Schranken, Quantitative Risk Management, Value at Risk, Correlation Matrix, Risk Aggregation, Fréchet-Hoeffding-Bounds |
| JEL: | G G2 G22 |
| Date: | 2024 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:thkivw:284399&r=rmg |
| By: | Gabriel, Stefan (University of Vienna, Department of Finance, Vienna, Austria); Kunst, Robert M. (Institute for Advanced Studies and University of Vienna, Vienna, Austria) |
| Abstract: | We examine two major topics in the field of cryptocurrencies. On the one hand, we investigate possible long-run equilibrium relationships among ten major cryptocurrencies by applying two different cointegration tests. This analysis aims at constructing cointegrated portfolios that enable statistical arbitrage. Moreover, we find evidence for a connection between market volatility and the spread used for trading. The results of the trading strategies suggest that cointegrated portfolios based on the Johansen procedure generate the highest abnormal log-returns, both in-sample and out-of-sample. Five out of six trading strategies generate a positive overall profit and outperform a passive investment approach out-of-sample. The second part of the econometric analysis explores Granger causality between volatility and the spread. For this analysis, we implement two types of forecasting models for Bitcoin volatility: the GARCH (generalized autoregressive conditional heteroskedasticity) family using daily price data and the HAR (Heterogeneous AutoRegressive) model family based on 5-min high-frequency data. In both categories, we also consider potential jumps in the price series, as we found that price jumps play an important role in Bitcoin volatility forecasts. The findings indicate that the realized GARCH model is the only GARCH model that can compete against the HAR-RV (Heterogeneous Autoregressive Realized Volatility) model in out-of-sample forecasting. |
| Keywords: | cryptocurrencies, bitcoin volatility, realized variance, jump variation, cointegrated portfolios, statistical arbitrage |
| JEL: | C22 C52 C53 |
| Date: | 2024–03 |
| URL: | http://d.repec.org/n?u=RePEc:ihs:ihswps:52&r=rmg |
| By: | Joshua Aslett; Gustavo González; Stuart Hamilton; Miguel Pecho |
| Abstract: | This technical note introduces analytics for compliance risk management in tax administration. Together with its accompanying toolkit, the note is intended as a starter kit to support capacity development in compliance planning, risk, and intelligence groups. Developed primarily for emerging analysts new to tax administration, the note presents both theory and practical aspects of analytics. Its toolkit is comprised of an initial collection of analytics templates designed to assist in turning the theory presented into practice in the areas of: (1) compliance planning; (2) taxpayer profiling; and (3) audit case selection. |
| Keywords: | tax administration; compliance risk management; compliance strategy; risk analysis; intelligence; data; analytics; digitalization; information technology; analytics support compliance risk management; support CRM analytics capability; CRM theory; IMF Library; data quality; Tax administration core functions; Machine learning; Value-added tax |
| Date: | 2024–02–26 |
| URL: | http://d.repec.org/n?u=RePEc:imf:imftnm:2024/001&r=rmg |
| By: | Steven Y. K. Wong; Jennifer S. K. Chan; Lamiae Azizi |
| Abstract: | Time-series with time-varying variance pose a unique challenge to uncertainty quantification (UQ) methods. Time-varying variance, such as volatility clustering as seen in financial time-series, can lead to large mismatch between predicted uncertainty and forecast error. Building on recent advances in neural network UQ literature, we extend and simplify Deep Evidential Regression and Deep Ensembles into a unified framework to deal with UQ under the presence of volatility clustering. We show that a Scale Mixture Distribution is a simpler alternative to the Normal-Inverse-Gamma prior that provides favorable complexity-accuracy trade-off. To illustrate the performance of our proposed approach, we apply it to two sets of financial time-series exhibiting volatility clustering: cryptocurrencies and U.S. equities. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.14476&r=rmg |
| By: | Elena Capatina; Gary Hansen; Minchung Hsu |
| Abstract: | This paper compares the impact of long term care (LTC) risk on single and married households and studies the roles played by informal care (IC), consumption sharing within households, and Medicaid in insuring this risk. We develop a life-cycle model where individuals face survival and health risk, including the possibility of becoming highly disabled and needing LTC. Households are heterogeneous in various important dimensions including education, productivity, and the age difference between spouses. Health evolves stochastically. Agents make consumption-savings decisions in a framework featuring an LTC state-dependent utility function. We find that household expenditures increase significantly when LTC becomes necessary, but married individuals are well insured against LTC risk due to IC. However, they still hold considerable assets due to the concern for the spouse who might become a widow/widower and can expect much higher LTC costs. IC significantly reduces precautionary savings for middle and high income groups, but interestingly, it encourages asset accumulation among low income groups because it reduces the probability of means-tested Medicaid LTC. |
| JEL: | D16 E21 H31 J14 |
| Date: | 2024–03 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:32196&r=rmg |
| By: | Ying Wu; Garvit Arora; Xuan Mei |
| Abstract: | Forecasting the loss given default (LGD) for defaulted Commercial Real Estate (CRE) loans poses a significant challenge due to the extended resolution and workout time associated with such defaults, particularly in CCAR and CECL framework where the utilization of post-default information, including macroeconomic variables (MEVs) such as unemployment (UER) and various rates, is restricted. The current environment of persistent inflation and resultant elevated rates further compounds the uncertainty surrounding predictive LGD models. In this paper, we leverage both internal and public data sources, including observations from the COVID-19 period, to present a list of evidence indicating that the growth rates of the Consumer Price, such as Year-over-Year (YoY) growth and logarithmic growth, are good leading indicators for various CRE related rates and indices. These include the Federal Funds Effective Rate and CRE market sales price indices in key locations such as Los Angeles, New York, and nationwide, encompassing both apartment and office segments. Furthermore, with CRE LGD data we demonstrate how incorporating CPI at the time of default can improve the accuracy of predicting CRE workout LGD. This is particularly helpful in addressing the common issue of early downturn underestimation encountered in CRE LGD models. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.15498&r=rmg |
| By: | Colombo, Jéfferson Augusto; Yarovaya, Larisa |
| Abstract: | Cryptocurrencies and blockchain have become a global phenomenon, transforming people’s relationships with technology and offering innovative tools for businesses and individuals to strive in a digital age. However, little is still known about the main drivers of cryptocurrency ownership, especially in emerging markets. Based on a representative online survey among 573 Brazilian digital platform investors, we find that crypto investors tend to be young, male, more tolerant to risk, less optimistic in their economic views, and consider themselves as ‘better’ investors compared to non-crypto online traders. While crypto and non-crypto investors have similar educational backgrounds, our results show that cryptocurrency literacy positively and strongly relates to cryptocurrency ownership and intentions to invest in cryptocurrency. A gender gap among cryptocurrency investors has been confirmed. The findings further suggest that sophisticated investors are more likely to hedge pessimistic economic expectations using cryptocurrency than their unsophisticated peers. We also find significant heterogeneity among cryptocurrency investors (e.g., early x late adopters) on attitudes and beliefs. The insights into digital investors’ intentions to invest in cryptocurrency can be valuable for policymakers in designing strategies for the broader adoption of digital assets in the era of a decentralized economy, considering the planned adoption of CBDC in Brazil. |
| Date: | 2024–02–29 |
| URL: | http://d.repec.org/n?u=RePEc:fgv:eesptd:568&r=rmg |