nep-rmg New Economics Papers
on Risk Management
Issue of 2022‒12‒19
seventeen papers chosen by

  1. A new encoding of implied volatility surfaces for their synthetic generation By Zheng Gong; Wojciech Frys; Renzo Tiranti; Carmine Ventre; John O'Hara; Yingbo Bai
  2. Stochastic Algorithms for Advanced Risk Budgeting By Adil Rengim Cetingoz; Jean-David Fermanian; Olivier Gu\'eant
  3. A complex networks based analysis of jump risk in equity returns: An evidence using intraday movements from Pakistan stock market By Faheem Aslam; Yasir Tariq Mohmand; Saqib Aziz; Jamal Ouenniche
  4. Italian subsidised crop insurance: what the role of policy changes By Fabio G., Santeramo; Ilaria, Russo; Emilia, Lamonaca
  5. Conditional divergence risk measures By Giulio Principi; Fabio Maccheroni
  6. A Supervisory Perspective on the U.S. Banking System By Dianne Dobbeck
  7. Chronicle of a death foretold: does higher volatility anticipate corporate default? By Ampudia, Miguel; Busetto, Filippo; Fornari, Fabio
  8. Forecasting Bitcoin volatility spikes from whale transactions and CryptoQuant data using Synthesizer Transformer models By Dorien Herremans; Kah Wee Low
  9. Online Investor Sentiment via Machine Learnings By Zongwu Cai; Pixiong Chen
  10. Bank lending rates and the remuneration for risk: evidence from portfolio and loan level data By Durrani, Agha; Metzler, Julian; Michail, Nektarios; Werner, Johannes Gabriel
  11. ESG Factors and Firms’ Credit Risk By Bonacorsi, Laura; Cerasi, Vittoria; Galfrascoli, Paola; Manera, Matteo
  12. Randomization of Short-Rate Models, Analytic Pricing and Flexibility in Controlling Implied Volatilities By Lech A. Grzelak
  13. Farm Loan Concentration and Financial Risk By Sylvanus, Gaku; Ifft, Jennifer; Byers, Luke
  14. Approximate Pricing of Derivatives Under Fractional Stochastic Volatility Model By Yuecai Han; Xudong Zheng
  15. Realized Illiquidity By Demetrio Lacava; Angelo Ranaldo; Paolo Santucci de Magistris
  16. Using multimodal learning and deep generative models for corporate bankruptcy prediction By Rogelio A. Mancisidor
  17. Technology-Based Risk Management for Rural Sectors and Natural Disasters in Developing Countries By Dayal Saraswat, Kinshuk

  1. By: Zheng Gong; Wojciech Frys; Renzo Tiranti; Carmine Ventre; John O'Hara; Yingbo Bai
    Abstract: In financial terms, an implied volatility surface can be described by its term structure, its skewness and its overall volatility level. We use a PCA variational auto-encoder model to perfectly represent these descriptors into a latent space of three dimensions. Our new encoding brings significant benefits for synthetic surface generation, in that (i) scenario generation is more interpretable; (ii) volatility extrapolation achieve better accuracy; and, (iii) we propose a solution to infer implied volatility surfaces of a stock from an index to which it belongs directly by modelling their relationship on the latent space of the encoding. All these applications, and the latter in particular, have the potential to improve risk management of financial derivatives whenever data is scarce.
    Date: 2022–11
  2. By: Adil Rengim Cetingoz; Jean-David Fermanian; Olivier Gu\'eant
    Abstract: Modern portfolio theory has provided for decades the main framework for optimizing portfolios. Because of its sensitivity to small changes in input parameters, especially expected returns, the mean-variance framework proposed by Markowitz (1952) has however been challenged by new construction methods that are purely based on risk. Among risk-based methods, the most popular ones are Minimum Variance, Maximum Diversification, and Risk Budgeting (especially Equal Risk Contribution) portfolios. Despite some drawbacks, Risk Budgeting is particularly attracting because of its versatility: based on Euler's homogeneous function theorem, it can indeed be used with a wide range of risk measures. This paper presents sound mathematical results regarding the existence and the uniqueness of Risk Budgeting portfolios for a very wide spectrum of risk measures and shows that, for many of them, computing the weights of Risk Budgeting portfolios only requires a standard stochastic algorithm.
    Date: 2022–11
  3. By: Faheem Aslam (COMSATS University Islamabad); Yasir Tariq Mohmand (COMSATS University Islamabad); Saqib Aziz (ESC [Rennes] - ESC Rennes School of Business); Jamal Ouenniche (University of Edinburgh)
    Abstract: We employ a multi-stage methodology combining complex network analytics and financial risk modelling to unveil the correlation structures amongst the price jump risks of companies forming the KSE-100 index in Pakistan. We identify the most influential companies in terms of jump risk, and identify communities — clusters of companies with similar price movement characteristics or with highly correlated price jumps. We find that equities in Pakistan stock market experience jumps in different time periods that are correlated to varying degrees within and across industries resulting in 19 different communities, four of which are strongly connected. While Oil & Gas, Cement and Banking sectors exhibit a significant representation of firms in communities, the automobile industry, however, seems to play an important role in risk propagation. These results provide an interesting insight to investors and other stakeholders from an emerging market viewpoint identifying the major sectors driving the volatility of KSE-100 index.
    Keywords: Complex network analysis,Intraday returns,Realised jumps,Realised volatility,Jump risk
    Date: 2020–12
  4. By: Fabio G., Santeramo; Ilaria, Russo; Emilia, Lamonaca
    Abstract: Risk management in agriculture is crucial and policymakers are implementing policy reforms to foster farmers’ adoption of ex-ante risk management tools such as crop insurance: their effectiveness is the core of policy evaluations exercises. The Italian subsidised crop insurance market has been interested by major reforms in 2013 and 2015. The 2013 reform removed subsidies to the mono-risk insurance contracts, whereas the 2015 reform replaced the multi- and pluri-risks contract schemes with packages, devoted to providing coverage over different set of adversities, thus altering the framework that has been used for several years. We highlight a correlation between the first reform and a drop in the quantity of insurance purchased, and between the latter reform and an increase in the value of the purchased insurance.
    Keywords: agricultural insurance; reforms; policy changes; insured acreage; insured value per hectare; subsidized agricultural insurance demand
    JEL: G22 Q14 Q18
    Date: 2022
  5. By: Giulio Principi; Fabio Maccheroni
    Abstract: Our paper contributes to the theory of conditional risk measures and conditional certainty equivalents. We adopt a random modular approach which proved to be effective in the study of modular convex analysis and conditional risk measures. In particular, we study the conditional counterpart of optimized certainty equivalents. In the process, we provide representation results for niveloids in the conditional $L^{\infty}$-space. By employing such representation results we retrieve a conditional version of the variational formula for optimized certainty equivalents. In conclusion, we apply this formula to provide a variational representation of the conditional entropic risk measure.
    Date: 2022–11
  6. By: Dianne Dobbeck
    Abstract: Remarks at the Financial Times Global Banking Summit (delivered via videoconference).
    Keywords: supervision; banking system; risk management
    Date: 2022–12–01
  7. By: Ampudia, Miguel; Busetto, Filippo; Fornari, Fabio
    Abstract: We test whether a simple measure of corporate insolvency based on equity return volatility -and denoted as Distance to Insolvency (DI) - delivers better prediction of corporate defaults than the widely-used Expected Default Frequency (EDF) measure computed by Moody’s. We look at the predictive power that current DIs and EDFs have for future defaults, both at a firm-level and at an aggregate level. At the granular level, both DIs and EDFs anticipate corporate defaults, but the DI contains information over and above the EDF, especially at longer forecasting horizons. At an aggregate level the DI shows superior forecasting power compared to the EDF, for horizons between 3 and 12 months. We illustrate the predictive power of the DI measure for the aggregate default rate by examining how corporate defaults would have evolved during the period marked by the spreading of the COVID-19 pandemic if DIs had not increased (so making future defaults less likely) also owing to the Eurosystem’s Public Emergency Purchase Program (PEPP). JEL Classification: C53, C58, G33
    Keywords: default probability, distance to insolvency, equity volatility, expected default frequency
    Date: 2022–11
  8. By: Dorien Herremans; Kah Wee Low
    Abstract: The cryptocurrency market is highly volatile compared to traditional financial markets. Hence, forecasting its volatility is crucial for risk management. In this paper, we investigate CryptoQuant data (e.g. on-chain analytics, exchange and miner data) and whale-alert tweets, and explore their relationship to Bitcoin's next-day volatility, with a focus on extreme volatility spikes. We propose a deep learning Synthesizer Transformer model for forecasting volatility. Our results show that the model outperforms existing state-of-the-art models when forecasting extreme volatility spikes for Bitcoin using CryptoQuant data as well as whale-alert tweets. We analysed our model with the Captum XAI library to investigate which features are most important. We also backtested our prediction results with different baseline trading strategies and the results show that we are able to minimize drawdown while keeping steady profits. Our findings underscore that the proposed method is a useful tool for forecasting extreme volatility movements in the Bitcoin market.
    Date: 2022–10
  9. By: Zongwu Cai (Department of Economics, The University of Kansas, Lawrence, KS 66045, USA); Pixiong Chen (Department of Economics, The University of Kansas, Lawrence, KS 66045, USA)
    Abstract: In this paper, we propose to utilize machine learning methods to determine the expected aggregated stock market risk premium based on online investor sentiment. Our empirical studies provide a strong evidence that some machine learning methods, such as the extreme gradient boosting or random forest, show significant predictive ability in terms of out-of-sample R-square with high-dimensional investor sentiment proxies. They also outperform the traditional linear models, which reveal a possible unobserved nonlinear relationship between online investor sentiment and risk premium. Moreover, this predictability based on online investor sentiment has a better economic value that it improves portfolio performance for investors who need to decide the optimal asset allocation in terms of certainty equivalent return gain and Sharpe ratio.
    JEL: C45 C55 C58 G11 G17
    Date: 2022–11
  10. By: Durrani, Agha; Metzler, Julian; Michail, Nektarios; Werner, Johannes Gabriel
    Abstract: We employ interest rates and expected loss probabilities from the 2021 EBA Stress Test dataset and euro area credit registries to examine whether the risk-return relationship holds in banking. After controlling for bank, loan, and debtor characteristics as well as macroeconomic conditions, results indicate that a risk-return relationship in bank lending is present but varies significantly across and within borrower segments. While bank lending rates appear to be quite responsive to risks towards households, results suggest that banks only significantly increase interest rates towards non-financial corporations that reside in the riskiest quantiles of the distribution. This potentially implies the presence of a cross-subsidization effect of credit risk. JEL Classification: E51, E52, E58
    Keywords: banking, credit register, interest rates, loans, risk-return
    Date: 2022–11
  11. By: Bonacorsi, Laura; Cerasi, Vittoria; Galfrascoli, Paola; Manera, Matteo
    Abstract: We study the relationship between the risk of default and Environmental, Social and Governance (ESG) factors using Supervised Machine Learning (SML) techniques on a cross-section of European listed companies. Our proxy for credit risk is the z-score originally proposed by Altman (1968). We consider an extensive number of ESG raw factors sourced from the rating provider MSCI as potential explanatory variables. In a first stage we show, using different SML methods such as LASSO and Random Forest, that a selection of ESG factors, in addition to the usual accounting ratios, helps explaining a firm’s probability of default. In a second stage, we measure the impact of the selected variables on the risk of default. Our approach provides a novel perspective to understand which environmental, social responsibility and governance characteristics may reinforce the credit score of individual companies.
    Keywords: Financial Economics, Productivity Analysis, Research Methods/ Statistical Methods
    Date: 2022–11–29
  12. By: Lech A. Grzelak
    Abstract: We focus on extending existing short-rate models, enabling control of the generated implied volatility while preserving analyticity. We achieve this goal by applying the Randomized Affine Diffusion (RAnD) method to the class of short-rate processes under the Heath-Jarrow-Morton framework. Under arbitrage-free conditions, the model parameters can be exogenously stochastic, thus facilitating additional degrees of freedom that enhance the calibration procedure. We show that with the randomized short-rate models, the shapes of implied volatility can be controlled and significantly improve the quality of the model calibration, even for standard 1D variants. In particular, we illustrate that randomization applied to the Hull-White model leads to dynamics of the local volatility type, with the prices for standard volatility-sensitive derivatives explicitly available. The randomized Hull-White (rHW) model offers an almost perfect calibration fit to the swaption implied volatilities.
    Date: 2022–11
  13. By: Sylvanus, Gaku; Ifft, Jennifer; Byers, Luke
    Keywords: Agricultural Finance
    Date: 2022
  14. By: Yuecai Han; Xudong Zheng
    Abstract: We investigate the problem of pricing derivatives under a fractional stochastic volatility model. We obtain an approximate expression of the derivative price where the stochastic volatility can be composed of deterministic functions of time and fractional Ornstein-Uhlenbeck process. Numerical simulations are given to illustrate the feasibility and operability of the approximation, and also demonstrate the effect of long-range on derivative prices.
    Date: 2022–10
  15. By: Demetrio Lacava (University of Messina - Department of Economics); Angelo Ranaldo (University of St. Gallen; Swiss Finance Institute); Paolo Santucci de Magistris (Luiss University of Rome)
    Abstract: We study the theoretical and empirical properties of a simple measure of market illiquidity, namely the realized Amihud, which is defined as the ratio between the realized volatility and trading volume and which refines the popular price impact measure proposed by Amihud (2002). In our model, both price volatility and market liquidity are assumed to follow stochastic processes in continuous time. In this setting, characterized by stochastic volatility and liquidity, we prove that the realized Amihud provides a precise measurement of the inverse of integrated liquidity over fixed-length periods (e.g., a day, a week, a month). We consider a number of alternative econometric specifications, hence highlighting the main dynamic and distributional properties of the realized Amihud, including jumps, clustering, and leverage effects.
    Keywords: Liquidity, Stochastic Volatility, Trading Volume, Amihud, Jumps
    JEL: C15 F31 G12 G15
    Date: 2022–11
  16. By: Rogelio A. Mancisidor
    Abstract: This research introduces for the first time the concept of multimodal learning in bankruptcy prediction models. We use the Conditional Multimodal Discriminative (CMMD) model to learn multimodal representations that embed information from accounting, market, and textual modalities. The CMMD model needs a sample with all data modalities for model training. At test time, the CMMD model only needs access to accounting and market modalities to generate multimodal representations, which are further used to make bankruptcy predictions. This fact makes the use of bankruptcy prediction models using textual data realistic and possible, since accounting and market data are available for all companies unlike textual data. The empirical results in this research show that the classification performance of our proposed methodology is superior compared to that of a large number of traditional classifier models. We also show that our proposed methodology solves the limitation of previous bankruptcy models using textual data, as they can only make predictions for a small proportion of companies. Finally, based on multimodal representations, we introduce an index that is able to capture the uncertainty of the financial situation of companies during periods of financial distress.
    Date: 2022–10
  17. By: Dayal Saraswat, Kinshuk
    Abstract: There are many risks associated with living in a developing country, especially in far-flung rural areas, where these risks are more prevalent, because they are often located in remote areas, where these risks are more prevalent, as they are frequently located in far-flung rural areas, where these risks are more prevalent. Managing risk requires the use of information that is up-to-date, and emerging technologies are providing highly cost-effective methods for collecting, storing, processing, and disseminating information about risk that is up-to-date in a cost-effective manner. Farmers are now able to receive early warnings regarding adverse weather conditions, market movements, and outbreaks of pests and diseases through the use of early warning systems which can be accessed through mobile apps and the internet. By using instruments such as insurance contracts and futures contracts, there is a limited amount of emerging technologies that can be utilized to transfer rural sector risk in the form of instruments. The development of these applications is hindered by the lack of institutional development, the high cost of the products, as well as an inability to customize them in order to meet the needs of smallholders. As a result, they are hampered by the fact that there are limitations to the amount of information which can be produced by technology.
    Keywords: Rural sector and risk management, technology based risk management, natural disasters and rural sector, mitigating risk in rural areas.
    JEL: M11 M15 O1 O14 Q16
    Date: 2022–10–16

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.