nep-rmg New Economics Papers
on Risk Management
Issue of 2023‒08‒21
25 papers chosen by

  1. Systemic risk indicator based on implied and realized volatility By Pawe{\l} Sakowski; Rafa{\l} Sieradzki; Robert \'Slepaczuk
  2. The Effect of COVID-19 on Cryptocurrencies and the Stock Market Volatility -- A Two-Stage DCC-EGARCH Model Analysis By Apostolos Ampountolas
  3. Financial Stress and Realized Volatility: The Case of Agricultural Commodities By Matteo Bonato; Oguzhan Cepni; Rangan Gupta; Christian Pierdzioch
  4. First passage times in portfolio optimization: a novel nonparametric approach By Paulo M.M. Rodrigues; Gabriel Zsurkis; João Nicolau
  5. Address Challenges Markowitz (1952) Faces: A New Measure of Asset Risk By Nie, Georege Yulin
  6. An elementary proof of the dual representation of Expected Shortfall By Martin Herdegen; Cosimo Munari
  7. The Transmission of Global Risk By Martin Bodenstein; Pablo A. Cuba-Borda; Albert Queraltó
  8. Supervised portfolios By Guillaume Chevalier; Guillaume Coqueret; Thomas Raffinot
  9. Differentiation in Risk Profiles By Christina Brinkmann
  10. Systemically important banks - emerging risk and policy responses: An agent-based investigation By Lilit Popoyan; Mauro Napoletano; Andrea Roventini
  11. How political tensions and geopolitical risks impact oil prices? By Valérie Mignon; Jamel Saadaoui
  12. Exploring the Dynamics of the Specialty Insurance Market Using a Novel Discrete Event Simulation Framework: a Lloyd's of London Case Study By Sedar Olmez; Akhil Ahmed; Keith Kam; Zhe Feng; Alan Tua
  13. Granular Corporate Hedging Under Dominant Currency By Laura Alfaro; Mauricio Calani; Liliana Varela
  14. Estimating the roughness exponent of stochastic volatility from discrete observations of the realized variance By Xiyue Han; Alexander Schied
  15. Risk Classification with On-Demand Insurance By Alexander Braun; Niklas Häusle; Paul D. Thistle
  16. Wishful Thinking is Risky Thinking: A Statistical-Distance Based Approach By Jarrod Burgh; Emerson Melo
  17. Risk Preference Types, Limited Consideration, and Welfare By Levon Barseghyan; Francesca Molinari
  18. On the Guyon-Lekeufack Volatility Model By Marcel Nutz; Andr\'es Riveros Valdevenito
  19. To use or not to use? Capital buffers and lending during a crisis By Lucas Avezum; Vítor Oliveira; Diogo Serra
  20. Rough PDEs for local stochastic volatility models By Peter Bank; Christian Bayer; Peter K. Friz; Luca Pelizzari
  21. The market for inflation risk By Bahaj, Saleem; Czech, Robert; Ding, Sitong; Reis, Ricardo
  22. "Generalized Extreme Value Approximation to the CUMSUMQ Test for Constant Unconditional Variance in Heavy-Tailed Time Series". By Josep Lluís Carrion-i-Silvestre; Andreu Sansó
  23. analysis of the predictor of a volatility surface by machine learning By Valentin Lourme
  24. Effects of extreme temperature on the European equity market By Bellocca, Gian Pietro Enzo; Alessi, Lucia; Poncela Blanco, Maria Pilar; Ruiz Ortega, Esther
  25. Machine learning for option pricing: an empirical investigation of network architectures By Laurens Van Mieghem; Antonis Papapantoleon; Jonas Papazoglou-Hennig

  1. By: Pawe{\l} Sakowski; Rafa{\l} Sieradzki; Robert \'Slepaczuk
    Abstract: We propose a new measure of systemic risk to analyze the impact of the major financial market turmoils in the stock markets from 2000 to 2023 in the USA, Europe, Brazil, and Japan. Our Implied Volatility Realized Volatility Systemic Risk Indicator (IVRVSRI) shows that the reaction of stock markets varies across different geographical locations and the persistence of the shocks depends on the historical volatility and long-term average volatility level in a given market. The methodology applied is based on the logic that the simpler is always better than the more complex if it leads to the same results. Such an approach significantly limits model risk and substantially decreases computational burden. Robustness checks show that IVRVSRI is a precise and valid measure of the current systemic risk in the stock markets. Moreover, it can be used for other types of assets and high-frequency data. The forecasting ability of various SRIs (including CATFIN, CISS, IVRVSRI, SRISK, and Cleveland FED) with regard to weekly returns of S&P 500 index is evaluated based on the simple linear, quasi-quantile, and quantile regressions. We show that IVRVSRI has the strongest predicting power among them.
    Date: 2023–07
  2. By: Apostolos Ampountolas
    Abstract: This research examines the correlations between the return volatility of cryptocurrencies, global stock market indices, and the spillover effects of the COVID-19 pandemic. For this purpose, we employed a two-stage multivariate volatility exponential GARCH (EGARCH) model with an integrated dynamic conditional correlation (DCC) approach to measure the impact on the financial portfolio returns from 2019 to 2020. Moreover, we used value-at-risk (VaR) and value-at-risk measurements based on the Cornish-Fisher expansion (CFVaR). The empirical results show significant long- and short-term spillover effects. The two-stage multivariate EGARCH model's results show that the conditional volatilities of both asset portfolios surge more after positive news and respond well to previous shocks. As a result, financial assets have low unconditional volatility and the lowest risk when there are no external interruptions. Despite the financial assets' sensitivity to shocks, they exhibit some resistance to fluctuations in market confidence. The VaR performance comparison results with the assets portfolios differ. During the COVID-19 outbreak, the Dow (DJI) index reports VaR's highest loss, followed by the S&P500. Conversely, the CFVaR reports negative risk results for the entire cryptocurrency portfolio during the pandemic, except for the Ethereum (ETH).
    Date: 2023–07
  3. By: Matteo Bonato (Department of Economics and Econometrics, University of Johannesburg, Auckland Park, South Africa; IPAG Business School, 184 Boulevard Saint-Germain, 75006 Paris, France); Oguzhan Cepni (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa); Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa); Christian Pierdzioch (Department of Economics, Helmut Schmidt University, Holstenhofweg 85, P.O.B. 700822, 22008 Hamburg, Germany)
    Abstract: Given recent debates about the financialization of commodity markets, we analyze the predictive power of financial stress for the realized volatility of agricultural commodity price returns. We estimate realized volatility from high-frequency intra-day data, where the sample period ranges from 2009 to 2020. We study the in-sample and out-of-sample predictability of realized volatility using variants of the popular heterogeneous autoregressive (HAR) model for realized volatility. We analyze the predictive value of financial stress by region of origin and by financial source, and we also control for various realized moments (leverage, realized skewness, realized kurtosis, realized jumps, realized upside tail risk, and realized downside tail risk). We find evidence of in-sample predictive value of financial stress for realized volatility, consistent with the financialialization hypothesis. This in-sample evidence, however, in general does not extend to an out-of-sample forecasting environment.
    Keywords: Realized volatility, Agricultural commodities, Financialization, Realized moments, Predictability
    JEL: C22 C53 G41 Q10
    Date: 2023–07
  4. By: Paulo M.M. Rodrigues; Gabriel Zsurkis; João Nicolau
    Abstract: This paper introduces a portfolio optimization procedure that aims to minimize the intrahorizon (IH) risk subject to a minimum expected time to achieve a target cumulative return. To estimate the first passage probabilities and the expected time a novel nonparametric method and a new Markov chain order determination approach are developed. The optimization framework proposed allows us to include novel path-dependent measures of risk and return in the asset allocation problem. An empirical application to S&P 100 companies, a risk-free asset and stock indices is provided. Our empirical results suggest that the proposed framework exhibits more consistency between in-sample and out-of-sample performance than the meanvariance model and an alternative optimization problem that minimizes the MaxVaR measure of Boudoukh et al. (2004). Overall, the portfolio optimization approach we introduce results in higher out-of-sample annualized returns for relatively low levels of IH risk.
    JEL: C14 C22 C41 G11 G17
    Date: 2023
  5. By: Nie, Georege Yulin (Concordia University)
    Abstract: Markowitz (1952) asset risk has long been challenged. First, asset risk has to be cumulative, because asset holder’s risk approaches zero as time length approaches zero (Nie, 2022a). Second, volatility does not decrease asset value while volatility of a lognormal distribution actually raises asset value. Third, support to Markowitz asset risk appears to arise from a confusion between asset value and wealth utility—the law of diminishing marginal utility supports that volatility reduces the latter. To address the challenges, we argue that asset risk causes volatility, but not vice versa, implying that volatility improperly represents asset risk, which cannot be diversified away. We delineate expected value (which asset risk impacts without a distribution) and volatility (which does not affect the former while following a quasi-normal distribution we proposed). We show that our firm risk, captured as equity risk premium, solves issues that have long been challenging agency and contracting theories.
    Date: 2023–07–13
  6. By: Martin Herdegen; Cosimo Munari
    Abstract: We provide an elementary proof of the dual representation of Expected Shortfall on the space of integrable random variables over a general probability space. Unlike the results in the extant literature, our proof only exploits basic properties of quantile functions and can thus be easily implemented in any graduate course on risk measures. As a byproduct, we obtain a new proof of the subadditivity of Expected Shortfall.
    Date: 2023–06
  7. By: Martin Bodenstein; Pablo A. Cuba-Borda; Albert Queraltó
    Abstract: Turmoil in the banking sector in the U.S. and Europe in early 2023 brought jitters to financial markets and increased concerns about a global risk-off event. Risk-off episodes—periods of increased global risk aversion—are characterized by sharp increases in credit spreads, high volatility in equity markets, and appreciation of reserve currencies
    Date: 2023–06–27
  8. By: Guillaume Chevalier (AXA Investment Managers, Multi Asset Client Solutions, Quantitative Research - AXA); Guillaume Coqueret (EM - emlyon business school); Thomas Raffinot (AXA Investment Managers, Multi Asset Client Solutions, Quantitative Research - AXA)
    Abstract: We propose an asset allocation strategy that engineers optimal weights before feeding them to a supervised learning algorithm. In contrast to the traditional approaches, the machine is able to learn risk measures, preferences and constraints beyond simple expected returns, within a flexible, forward-looking and non-linear framework. Our empirical analysis illustrates that predicting the optimal weights directly instead of the traditional two step approach leads to more stable portfolios with statistically better risk-adjusted performance measures. To foster reproducibility and future comparisons, our code is publicly available on Google Colab.
    Date: 2022–12–02
  9. By: Christina Brinkmann
    Abstract: This paper offers a model of vertical product differentiation in derivatives markets. Two dealers that choose their risk profile offer insurance to clients who differ in risk aversion. For given risk profiles, a unique price equilibrium exists in which the dealer with the lower risk profile has larger profits. Under plausible conditions, market discipline in the choice of risk profiles emerges: the first mover chooses a low risk profile, and the second mover follows at an optimal distance. The result serves as a reference point when considering the effects of introducing a central counterparty (CCP) that removes the quality dimension of competition.
    Keywords: OTC Markets, Derivatives, Central Clearing, Imperfect Competition, Vertical Product Differentiation
    JEL: G12 G23 G28 L13 L15
    Date: 2023–07
  10. By: Lilit Popoyan; Mauro Napoletano; Andrea Roventini
    Abstract: We develop a macroeconomic agent-based model to study the role of systemically important banks (SIBs) in financial stability and the effectiveness of capital surcharges on SIBs as a risk management tool. The model is populated by heterogeneous firms, consumers, and banks interacting locally in different markets. In particular, banks provide credit to firms according to Basel III macro-prudential frameworks and manage their liquidity in the interbank market. The Central Bank performs monetary policy according to different types of Taylor rules. Our model endogenously generates banks with different balance sheet sizes, making some systemically important. The additional capital surcharges for SIBs prove to have a marginal effect on preventing the crisis since it points mainly to the ''too-big-to-fail'' problem with minimal importance for ''too-interconnected-to-fail'', ''too-many-to-fail'' and other issues. Moreover, we found that additional capital surcharges on SIBs do not account for the type and management strategy of the bank, leading to the ''one-size-fits-all'' problem. Finally, we found that additional loss-absorbing capacity needs to be increased to ensure total coverage of losses for failed SIBs.
    Keywords: Financial instability; monetary policy; macro-prudential policy; systemically important banks, additional loss-absorbing capacity, Basel III regulation; agent-based models.
    Date: 2023–07–28
  11. By: Valérie Mignon (University of Paris Nanterre and CEPII); Jamel Saadaoui (University of Strasbourg)
    Abstract: This paper assesses the effect of US-China political relationships and geopolitical risks on oil prices. To this end, we consider two quantitative measures – the Political Relationship Index (PRI) and the Geopolitical Risk Index (GPR) – and rely on structural VAR and local projections methodologies. We expand the literature on the macroeconomic consequences of geopolitical risks by considering bilateral political relationships. The bilateral GPR does not focus on the relation between the US and China; rather, it provides an overall picture of the geopolitical uncertainty for China on a multilateral basis. Our empirical investigation shows that improved US-China relationships, as well as higher geopolitical risks, drive up the price of oil. Indeed, unexpected shocks in the political relationship index are associated with optimistic expectations about economic activity, whereas unexpected shocks in the geopolitical risk index reflect fears of supply disruption. Political tensions and geopolitical risks are thus complementary causal drivers of oil prices, the former being linked to the demand side and the latter to the supply side.
    Keywords: Oil prices, political relationships, geopolitical risk, China
    JEL: F
    Date: 2023
  12. By: Sedar Olmez; Akhil Ahmed; Keith Kam; Zhe Feng; Alan Tua
    Abstract: This research presents a novel Discrete Event Simulation (DES) of the Lloyd's of London specialty insurance market, exploring complex market dynamics that have not been previously studied quantitatively. The proof-of-concept model allows for the simulation of various scenarios that capture important market phenomena such as the underwriting cycle, the impact of risk syndication, and the importance of appropriate exposure management. Despite minimal calibration, our model has shown that it is a valuable tool for understanding and analysing the Lloyd's of London specialty insurance market, particularly in terms of identifying areas for further investigation for regulators and participants of the market alike. The results generate the expected behaviours that, syndicates (insurers) are less likely to go insolvent if they adopt sophisticated exposure management practices, catastrophe events lead to more defined patterns of cyclicality and cause syndicates to substantially increase their premiums offered. Lastly, syndication enhances the accuracy of actuarial price estimates and narrows the divergence among syndicates. Overall, this research offers a new perspective on the Lloyd's of London market and demonstrates the potential of individual-based modelling (IBM) for understanding complex financial systems.
    Date: 2023–07
  13. By: Laura Alfaro (Harvard Business School; Centre for Economic Policy Research (CEPR); National Bureau of Economic Research (NBER)); Mauricio Calani (Central Bank of Chile); Liliana Varela (London School of Economics (LSE); Centre for Economic Policy Research (CEPR))
    Abstract: This paper shows that, in a world dominated by vehicle currencies, firms engaging in international operations retain currency risk and hedge it real and financially. We employ a unique dataset covering the universe of trade credit, international trade, foreign currency debt, and FX derivatives contracts with firms’ census data in Chile (2005-2018). We document that operational hedging is quantitatively limited, as different maturity, frequency, and amount of FX operations make it difficult to net these exposures. The granular firms complement real hedging using FX financial instruments, which improve their cash flow management and promote their trade and growth.
    Keywords: Operational Hedging, FX hedging, FX derivatives, cash flow, foreign currency debt, currency mismatch, trade credit, dominant currency
    JEL: F14 F2 F31 F38 F4 G30
    Date: 2023–02
  14. By: Xiyue Han; Alexander Schied
    Abstract: We consider the problem of estimating the roughness of the volatility in a stochastic volatility model that arises as a nonlinear function of fractional Brownian motion with drift. To this end, we introduce a new estimator that measures the so-called roughness exponent of a continuous trajectory, based on discrete observations of its antiderivative. We provide conditions on the underlying trajectory under which our estimator converges in a strictly pathwise sense. Then we verify that these conditions are satisfied by almost every sample path of fractional Brownian motion (with drift). As a consequence, we obtain strong consistency theorems in the context of a large class of rough volatility models. Numerical simulations show that our estimation procedure performs well after passing to a scale-invariant modification of our estimator.
    Date: 2023–07
  15. By: Alexander Braun (University of St. Gallen; Swiss Finance Institute); Niklas Häusle (University of St. Gallen); Paul D. Thistle (University of Nevada, Las Vegas)
    Abstract: On-demand insurance is an innovative business model from the InsurTech space, which provides coverage for episodic risks. It makes use of a simple fact in a practical way: People differ in their frequency of exposure as well as the probability of loss. The extra dimension of heterogeneity can be used to screen the insured and shifts the utility-possibility frontier outwards. We provide a sufficient condition under which type-specific full insurance at the actuarially fair price is incentive compatible. We also show that our results hold for various real-world implementations of on-demand insurance.
    Keywords: adverse selection, efficiency, risk classification, insurance, insurtech, business models
    JEL: D82 D86 G22
    Date: 2023–06
  16. By: Jarrod Burgh; Emerson Melo
    Abstract: We develop a model of wishful thinking that incorporates the costs and benefits of biased beliefs. We establish the connection between distorted beliefs and risk, revealing how wishful thinking can be understood in terms of risk measures. Our model accommodates extreme beliefs, allowing wishful-thinking decision-makers to assign zero probability to undesirable states and positive probability to otherwise impossible states. Furthermore, we establish that wishful thinking behavior is equivalent to quantile-utility maximization for the class of threshold beliefs distortion cost functions. Finally, exploiting this equivalence, we derive conditions under which an optimistic decision-maker prefers skewed and riskier choices.
    Date: 2023–07
  17. By: Levon Barseghyan; Francesca Molinari
    Abstract: We provide sufficient conditions for semi-nonparametric point identification of a mixture model of decision making under risk, when agents make choices in multiple lines of insurance coverage (contexts) by purchasing a bundle. As a first departure from the related literature, the model allows for two preference types. In the first one, agents behave according to standard expected utility theory with CARA Bernoulli utility function, with an agent-specific coefficient of absolute risk aversion whose distribution is left completely unspecified. In the other, agents behave according to the dual theory of choice under risk(Yaari, 1987) combined with a one-parameter family distortion function, where the parameter is agent-specific and is drawn from a distribution that is left completely unspecified. Within each preference type, the model allows for unobserved heterogeneity in consideration sets, where the latter form at the bundle level -- a second departure from the related literature. Our point identification result rests on observing sufficient variation in covariates across contexts, without requiring any independent variation across alternatives within a single context. We estimate the model on data on households' deductible choices in two lines of property insurance, and use the results to assess the welfare implications of a hypothetical market intervention where the two lines of insurance are combined into a single one. We study the role of limited consideration in mediating the welfare effects of such intervention.
    Date: 2023–07
  18. By: Marcel Nutz; Andr\'es Riveros Valdevenito
    Abstract: Guyon and Lekeufack recently proposed a path-dependent volatility model and documented its excellent performance in fitting market data and capturing stylized facts. The instantaneous volatility is modeled as a linear combination of two processes, one is an integral of weighted past price returns and the other is the square-root of an integral of weighted past squared volatility. Each of the weightings is built using two exponential kernels reflecting long and short memory. Mathematically, the model is a coupled system of four stochastic differential equations. Our main result is the wellposedness of this system: the model has a unique strong (non-explosive) solution for realistic parameter values. We also study the positivity of the resulting volatility process.
    Date: 2023–07
  19. By: Lucas Avezum; Vítor Oliveira; Diogo Serra
    Abstract: In this paper, we study the effect of having a greater management capital buffer on banks’ lending during a crisis. Using loan-level data merged with detailed supervisory data on banks’ balance sheets and regulatory requirements, we find that Portuguese banks with greater headroom above the overall capital requirement lent more to firms after the Covid-19 shock than banks with lower headroom, i.e., banks used, at least to some extent, their management buffers. The introduction of public-guarantee schemes in this period mitigated this effect as banks with lower capital headroom had the incentive to lend under these schemes. Moreover, we find that the effect of management buffer on lending is stronger for banks with lower market funding and more vulnerable firms, highlighting the importance of market pressure and risk aversion, respectively.
    JEL: E51 G28 H12
    Date: 2023
  20. By: Peter Bank; Christian Bayer; Peter K. Friz; Luca Pelizzari
    Abstract: In this work, we introduce a novel pricing methodology in general, possibly non-Markovian local stochastic volatility (LSV) models. We observe that by conditioning the LSV dynamics on the Brownian motion that drives the volatility, one obtains a time-inhomogeneous Markov process. Using tools from rough path theory, we describe how to precisely understand the conditional LSV dynamics and reveal their Markovian nature. The latter allows us to connect the conditional dynamics to so-called rough partial differential equations (RPDEs), through a Feynman-Kac type of formula. In terms of European pricing, conditional on realizations of one Brownian motion, we can compute conditional option prices by solving the corresponding linear RPDEs, and then average over all samples to find unconditional prices. Our approach depends only minimally on the specification of the volatility, making it applicable for a wide range of classical and rough LSV models, and it establishes a PDE pricing method for non-Markovian models. Finally, we present a first glimpse at numerical methods for RPDEs and apply them to price European options in several rough LSV models.
    Date: 2023–07
  21. By: Bahaj, Saleem (University College London and Bank of England); Czech, Robert (Bank of England); Ding, Sitong (London School of Economics); Reis, Ricardo (London School of Economics)
    Abstract: This paper uses transaction-level data on the universe of traded UK inflation swaps to characterise who buys and sells inflation risk, when, and with what price elasticity. This provides measures of expected inflation cleaned from liquidity frictions. We first show that this market is segmented: pension funds trade at long horizons while hedge funds trade at short horizons, with dealer banks as their counterparties in both markets. This segmentation suggests three identification strategies – sign restrictions, granular instrumental variables, and heteroskedasticity – for the demand and supply functions of each investor type. Across the three strategies, we find that (i) prices absorb new information within three days; (ii) the supply of long-horizon inflation protection is very elastic; and (iii) short-horizon price movements are unreliable measures of expected inflation as they primarily reflect liquidity shocks. Our counterfactual measure of long-horizon expected inflation in the absence of these shocks suggests that the risk of a deflation trap during the pandemic and of a persistent rise in inflation following the energy shocks were overstated, while since Autumn of 2022, expected inflation has been lower and falling more rapidly than conventional measures.
    Keywords: Asset demand system; monetary policy; anchored expectations; identification of demand and supply shocks.
    JEL: C30 E31 E44 G12
    Date: 2023–06–23
  22. By: Josep Lluís Carrion-i-Silvestre (AQR-IREA Research Group. Departament d’Econometria, Estadística i Economia Aplicada. Universitat de Barcelona. Av. Diagonal, 690. 08034 Barcelona. Spain.); Andreu Sansó (Department d’Economia Aplicada. Universitat de les Illes Balears and MOTIBO Research Group, Balearic Islands Health Research Institute (Idisba).)
    Abstract: This paper focuses on testing the stability of the unconditional variance when the stochastic processes may have heavy-tailed distributions. Finite sample distributions that depend both on the effective sample size and the tail index are approximated using Extreme Value distributions and summarized using response surfaces. A modification of the Iterative Cumulative Sum of Squares (ICSS) algorithm to detect the presence of multiple structural breaks is suggested, adapting the algorithm to the tail index of the underlying distribution of the process. We apply the algorithm to eighty absolute log-exchange rate returns, finding evidence of (i) infinite variance in about a third of the cases, (ii) finite changing unconditional variance for another third of the time series - totalling about one hundred structural breaks - and (iii) finite constant unconditional variance for the remaining third of the time series.
    Keywords: CUMSUMQ test, Unconditional variance, Multiple structural changes, Heavy tails, Generalized Extreme Value distribution. JEL classification: C12, C22.
    Date: 2023–07
  23. By: Valentin Lourme (Arts et Métiers ParisTech, Natixis)
    Abstract: The purpose of this study is to compare two approaches to assessing the points of a volatility layer. The first approach used is cubic spline interpolation, while the second approach is a machine learning algorithm, the XGBoost. The purpose of this comparison is to define the use case where the XGBoost Learning machine algorithm is more suitable compared to the cubic spline. The comparison between the two approaches is measured with the error between the measured volatility and the interpolated or predicted volatility. Cubic spline interpolation requires volatility data on the day of the study for interpolation to occur. The XGBoost Machine Learning algorithm will train on historical data to predict the volatility value on the day of the study.
    Abstract: Cette étude vise à comparer deux approches d'évaluation des points d'une nappe de volatilité. La première approche utilisée est l'interpolation par spline cubique, tandis que la seconde approche est un algorithme de machine Learning, le XGBoost. Cette comparaison a pour but de définir le cas d'utilisation ou l'algorithme de machine Learning XGBoost est plus adapté par rapport au spline cubique. La comparaison entre les deux approches est mesurée avec l'erreur entre la volatilité mesurée et la volatilité interpolée ou prédite. L'interpolation par spline cubique nécessite les données de volatilité au jour de l'étude pour que l'interpolation soit réalisée. L'algorithme de Machine Learning XGBoost va s'entrainer sur des données historiques pour prédire la valeur de volatilité au jour de l'étude
    Date: 2023–07–05
  24. By: Bellocca, Gian Pietro Enzo; Alessi, Lucia; Poncela Blanco, Maria Pilar; Ruiz Ortega, Esther
    Abstract: The increasing frequency and severity of extreme temperatures are potential threats to financial stability. Indeed, physical risk related to these extreme phenomena can affect the whole financial system and, in particular, the equity market. In this study, we analyze the impact of extreme temperature exposure on firms' performance in Europe over the XXI century. We show that extreme temperatures can affect firms' profitability depending on their industry and the quarter of the year. Our results are of interest for both investors operating in the equity market and for regulators in charge of securing financial stability.
    Keywords: Climate Change; Equity Market; Firm Performance; Physical Risk; Temperatures
    JEL: C23 C55 G12 G14 Q54
    Date: 2023–07–24
  25. By: Laurens Van Mieghem; Antonis Papapantoleon; Jonas Papazoglou-Hennig
    Abstract: We consider the supervised learning problem of learning the price of an option or the implied volatility given appropriate input data (model parameters) and corresponding output data (option prices or implied volatilities). The majority of articles in this literature considers a (plain) feed forward neural network architecture in order to connect the neurons used for learning the function mapping inputs to outputs. In this article, motivated by methods in image classification and recent advances in machine learning methods for PDEs, we investigate empirically whether and how the choice of network architecture affects the accuracy and training time of a machine learning algorithm. We find that for option pricing problems, where we focus on the Black--Scholes and the Heston model, the generalized highway network architecture outperforms all other variants, when considering the mean squared error and the training time as criteria. Moreover, for the computation of the implied volatility, after a necessary transformation, a variant of the DGM architecture outperforms all other variants, when considering again the mean squared error and the training time as criteria.
    Date: 2023–07

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.