nep-rmg New Economics Papers
on Risk Management
Issue of 2023‒05‒22
fourteen papers chosen by

  1. Less disagreement, better forecasts: adjusted risk measures in the energy futures market By Zhang, Ning; Gong, Yujing; Xue, Xiaohan
  2. Application of Machine Learning to a Credit Rating Classification Model: Techniques for Improving the Explainability of Machine Learning By Ryuichiro Hashimoto; Kakeru Miura; Yasunori Yoshizaki
  3. Covariance matrix estimation for robust portfolio allocation By Ahmad W. Bitar; Nathan de Carvalho; Valentin Gatignol
  4. Portfolio Optimization using Predictive Auxiliary Classifier Generative Adversarial Networks with Measuring Uncertainty By Jiwook Kim; Minhyeok Lee
  5. Particle MCMC in forecasting frailty correlated default models with expert opinion By Ha Nguyen
  6. Flip the coin: Heads, tails or cryptocurrencies? By António Manuel Portugal Duarte; Fátima Teresa Castelo Assunção Sol Murta; Nuno José Henriques Baetas da Silva; Beatriz Rodrigues Vieira
  7. Do Banks Hedge Using Interest Rate Swaps? By Lihong McPhail; Philipp Schnabl; Bruce Tuckman
  8. Transmission of risks between energy and agricultural commodities: Frequency time-varying VAR, asymmetry and portfolio management By Furuoka, Fumitaka; Yaya, OlaOluwa S; Ling, Piu Kiew; Al-Faryan, Mamdouh Abdulaziz Saleh; Islam, M. Nazmul
  9. Recurrent neural network based parameter estimation of Hawkes model on high-frequency financial data By Kyungsub Lee
  10. The antecedents of MNC political risk and uncertainty under right-wing populist governments By Sallai, Dorottya; Schnyder, Gerhard; Kinderman, Daniel; Nölke, Andreas
  11. Imperfect Banking Competition and the Propagation of Uncertainty Shocks By Tommaso Gasparini
  12. Debtor Fraud in Consumer Debt Renegotiation By Slava Mikhed; Sahil Raina; Barry Scholnick; Man Zhang
  13. One Threshold Doesn’t Fit All: Tailoring Machine Learning Predictions of Consumer Default for Lower-Income Areas By Vitaly Meursault; Daniel Moulton; Larry Santucci; Nathan Schor
  14. The Unpredictability of Individual-Level Longevity By Breen, Casey; Seltzer, Nathan

  1. By: Zhang, Ning; Gong, Yujing; Xue, Xiaohan
    Abstract: This paper develops a generic adjustment framework to improve in the market risk forecasts of diverse risk forecasting models, which indicates the degree to which risk is under- and overestimated. In the context of the energy commodity market, a market in which tail risk management is of crucial importance, the empirical analysis shows that after this adjustment framework is applied, the forecasting performance of various risk models generally improves, as verified by a battery of backtesting methods. Additionally, our method also lessens the risk model disagreement among post-adjusted risk forecasts.
    Keywords: energy futures; expected shortfall; finance; model disagreement; value at risk; ES/K002309/1; ES/R009724/1; Wiley deal
    JEL: C52 C53 G10
    Date: 2023–03–05
  2. By: Ryuichiro Hashimoto (Bank of Japan); Kakeru Miura (Bank of Japan); Yasunori Yoshizaki (Bank of Japan)
    Abstract: Machine learning (ML) has been used increasingly in a wide range of operations at financial institutions. In the field of credit risk management, many financial institutions are starting to apply ML to credit scoring models and default models. In this paper we apply ML to a credit rating classification model. First, we estimate classification models based on both ML and ordinal logistic regression using the same dataset to see how model structure affects the prediction accuracy of models. In addition, we measure variable importance and decompose model predictions using so-called eXplainable AI (XAI) techniques that have been widely used in recent years. The results of our analysis are twofold. First, ML captures more accurately than ordinal logit regression the nonlinear relationships between financial indicators and credit ratings, leading to a significant improvement in prediction accuracy. Second, SHAP (Shapley Additive exPlanations) and PDP (Partial Dependence Plot) show that several financial indicators such as total revenue, total assets turnover, and ICR have a significant impact on firms’ credit quality. Nonlinear relationships between financial indicators and credit rating are also observed: a decrease in ICR below about 2 lowers firms’ credit quality sharply. Our analysis suggests that using XAI while understanding its underlying assumptions improves the low explainability of ML.
    Keywords: Credit risk management; Machine learning; Explainability; eXplainable AI (XAI)
    JEL: C49 C55 G32
    Date: 2023–04–21
  3. By: Ahmad W. Bitar (UTT - Université de Technologie de Troyes, CentraleSupélec); Nathan de Carvalho (UPCité - Université Paris Cité, CentraleSupélec, Engie Global Markets); Valentin Gatignol (Qube Research and Technologies, CentraleSupélec)
    Abstract: In this technical report , we aim to combine different protfolio allocation techniques with covariance matrix estimators to meet two types of clients' requirements: client A who wants to invest money wisely, not taking too much risk, and not willing to pay too much in rebalancing fees; and client B who wants to make money quickly, benefit from market's short-term volatility, and ready to pay rebalancing fees. Four portfolio techniques are considered (mean-variance, robust portfolio, minimum-variance, and equi-risk budgeting), and four covariance estimators are applied (sample covariance, ordinary least squares (OLS) covariance, cross-validated eigenvalue shrinkage covariance, and eigenvalue clipping). Some comparisons between the covariance estimators in terms of eigenvalue stability and four metrics (i.e. expected risk, gross leverage, Sharpe ratio and effective diversification) exhibit the superiority of the eigenvalue clipping covariance estimator. The experiments on the Russel1000 dataset show that the minimum-variance with eigenvalue clipping is the model suitable for client A, whereas robust portfolio with eigenvalue clipping is the one suitable for client B.
    Keywords: Robust portfolio, minimum-variance, eigenvalue clipping, OLS covariance
    Date: 2023–03–26
  4. By: Jiwook Kim; Minhyeok Lee
    Abstract: In financial engineering, portfolio optimization has been of consistent interest. Portfolio optimization is a process of modulating asset distributions to maximize expected returns and minimize risks. To obtain the expected returns, deep learning models have been explored in recent years. However, due to the deterministic nature of the models, it is difficult to consider the risk of portfolios because conventional deep learning models do not know how reliable their predictions can be. To address this limitation, this paper proposes a probabilistic model, namely predictive auxiliary classifier generative adversarial networks (PredACGAN). The proposed PredACGAN utilizes the characteristic of the ACGAN framework in which the output of the generator forms a distribution. While ACGAN has not been employed for predictive models and is generally utilized for image sample generation, this paper proposes a method to use the ACGAN structure for a probabilistic and predictive model. Additionally, an algorithm to use the risk measurement obtained by PredACGAN is proposed. In the algorithm, the assets that are predicted to be at high risk are eliminated from the investment universe at the rebalancing moment. Therefore, PredACGAN considers both return and risk to optimize portfolios. The proposed algorithm and PredACGAN have been evaluated with daily close price data of S&P 500 from 1990 to 2020. Experimental scenarios are assumed to rebalance the portfolios monthly according to predictions and risk measures with PredACGAN. As a result, a portfolio using PredACGAN exhibits 9.123% yearly returns and a Sharpe ratio of 1.054, while a portfolio without considering risk measures shows 1.024% yearly returns and a Sharpe ratio of 0.236 in the same scenario. Also, the maximum drawdown of the proposed portfolio is lower than the portfolio without PredACGAN.
    Date: 2023–04
  5. By: Ha Nguyen
    Abstract: Predicting corporate default risk has long been a crucial topic in the finance field, as bankruptcies impose enormous costs on market participants as well as the economy as a whole. This paper aims to forecast frailty correlated default models with subjective judgements on a sample of U.S. public non-financial firms spanning January 1980-June 2019. We consider a reduced-form model and adopt a Bayesian approach coupled with the Particle Markov Chain Monte Carlo (Particle MCMC) algorithm to scrutinize this problem. The findings show that the volatility and the mean reversion of the hidden factor, which determine the dependence of the unobserved default intensities on the latent variable, have a highly economically and statistically significant positive impact on the default intensities of the firms. The results also indicate that the 1-year prediction for frailty correlated default models with different prior distributions is relatively good, whereas the prediction accuracy ratios for frailty-correlated default models with non-informative and subjective prior distributions over various prediction horizons are not significantly different.
    Date: 2023–04
  6. By: António Manuel Portugal Duarte (University of Coimbra, Centre for Business and Economics Research, CeBER and Faculty of Economics); Fátima Teresa Castelo Assunção Sol Murta (Univ of Coimbra, CeBER, Faculty of Economics); Nuno José Henriques Baetas da Silva (Ph.D. Student at Faculty of Economics, University of Coimbra); Beatriz Rodrigues Vieira (Univ Coimbra, Faculty of Economics)
    Abstract: This paper analysis and compares the volatility of seven cryptocurrencies – Bitcoin, Dogecoin, Ethereum, BitcoinCash, Ripple, Stellar and Litecoin – to the volatility of seven centralized currencies – Yuan, Yen, Canadian Dollar, Brazilian Real, Swiss Franc, Euro and British Pound. We estimate GARCH models to analyze their volatility. The results point to a considerably high volatility of cryptocurrencies when compared to that of centralized currencies. Therefore, we conclude that cryptocurrencies still fall far short of fulfilling all the requirements to be considered as a currency, specifically regarding the functions of store of value and unit of account.
    Keywords: Centralized currencies, cryptocurrencies; GARCH models; volatility.
    Date: 2023–03
  7. By: Lihong McPhail; Philipp Schnabl; Bruce Tuckman
    Abstract: We ask whether banks use interest rate swaps to hedge the interest rate risk of their assets, primarily loans and securities. To this end, we use regulatory data on individual swap positions for the largest 250 U.S. banks. We find that the average bank has a large notional amount of swaps-- $434 billion, or more than 10 times assets. But after accounting for the significant extent to which swap positions offset each other, the average bank has essentially no net interest rate risk from swaps: a 100-basis-point increase in rates increases the value of its swaps by 0.1% of equity. There is variation across banks, with some bank swap positions decreasing and some increasing with rates, but aggregating swap positions at the level of the banking system reveals that most swap exposures are offsetting. Therefore, as a description of prevailing practice, we conclude that swap positions are not economically significant in hedging the interest rate risk of bank assets.
    JEL: G21 G32
    Date: 2023–04
  8. By: Furuoka, Fumitaka; Yaya, OlaOluwa S; Ling, Piu Kiew; Al-Faryan, Mamdouh Abdulaziz Saleh; Islam, M. Nazmul
    Abstract: This paper examines energy and agricultural commodities' short-run and long-run connectedness by using the Time-varying parameter vector autoregressions (TVP-VAR). It applies the frequency version of the TVP-VAR model, which is a modified version of the dynamic TVP-VAR model. The frequency decomposition definition also decomposes into short-run and long-run connectedness. We further the analysis by investigating the effect of asymmetry in returns on connectedness. It also examines how portfolio management strategies would lead to a maximization of profits with minimal risks. Empirical evidence indicates that only 32.52% and 31.38% of connectedness in oil and gas, respectively, are transmitted to agricultural commodities, which suggests their weak tendencies in influencing agricultural commodities; the total connectedness index hovers around 40-60% in the 2018-2019 period; however, it dropped below 40% in 2020-2021 when the COVID-19 pandemic contributed to disintegrate the connectedness between energy and agricultural commodities but increased further during the 2022 Russia-Ukraine saga. The findings also indicate that corn, wheat, and flour are net transmitters of risks to oil and natural gas in the long and short-run, and wheat-flour pairwise connectedness is the strongest in the connectedness. Asymmetry is also pronounced in the network of connectedness. Portfolio analyses indicate that investors require a low proportion of energy in a portfolio of energy-agricultural commodities to achieve an optimum profit. The findings will offer exciting insights into the connectedness of agricultural and energy commodities, particularly during periods of high price uncertainty.
    Keywords: Agricultural commodity; Asymmetry; Frequency TVP-VAR; Optimal weight; Risk
    JEL: C22
    Date: 2023–02–03
  9. By: Kyungsub Lee
    Abstract: This study examines the use of a recurrent neural network for estimating the parameters of a Hawkes model based on high-frequency financial data, and subsequently, for computing volatility. Neural networks have shown promising results in various fields, and interest in finance is also growing. Our approach demonstrates significantly faster computational performance compared to traditional maximum likelihood estimation methods while yielding comparable accuracy in both simulation and empirical studies. Furthermore, we demonstrate the application of this method for real-time volatility measurement, enabling the continuous estimation of financial volatility as new price data keeps coming from the market.
    Date: 2023–04
  10. By: Sallai, Dorottya; Schnyder, Gerhard; Kinderman, Daniel; Nölke, Andreas
    Abstract: Right-wing populist parties who obtain governmental power rely on ethno-nationalist mobilization for domestic legitimacy. They may therefore adopt policies that explicitly seek to disadvantage foreign multinational corporations (MNCs). Understanding what factors increase a foreign MNC’s exposure to adverse action by right-wing populists is an understudied question in the field of international business policy. We investigate this question in post-socialist member states of the European Union, which constitute extreme cases of right-wing populist government power. As such, they constitute a fertile ground to further our theoretical understanding of the distinction between calculable political risk and incalculable political uncertainty. Through a case study-based theory-building approach, which draws on existing literature and interview data, we derive a series of propositions and develop a research agenda. We identify factors at the country-, sector-, and firm-level that influence exposure to adverse policy action by host-country governments. We explore when political risk may turn into political uncertainty and provide suggestions to foreign MNCs operating in right-wing populist contexts on how to reduce this uncertainty. Our study provides insights for policy makers too, who should be aware of the impact political shifts towards right-wing populist governments have on political uncertainty for foreign companies.
    Keywords: business–government relations; MNE–host-country relations; multinational corporations (MNCs) and enterprises (MNEs); political risk; populism; 462-19-080
    JEL: J50
    Date: 2023–04–05
  11. By: Tommaso Gasparini
    Abstract: Uncertainty shocks play a crucial role in driving business cycle fluctuations. This paper investigates the impact of changes in banking competition on the propagation of uncertainty shocks. Using a panel dataset of 44 countries, I show that lower banking competition amplifies the negative impact of uncertainty on output growth. I further explore this relationship through a dynamic stochastic general equilibrium model featuring imperfect banking competition and financial frictions. The model shows that lower banking competition leads to higher borrowing rates and increased risk-taking by entrepreneurs. As a result, when the number of competitors is lower, uncertainty shocks have a stronger negative impact on defaults, investment and output due to increased risk-taking.
    Keywords: Financial Frictions, Financial Intermediaries, Heterogeneous Agents, Market Power, Uncertainty
    JEL: E32 E44 G21 L13
    Date: 2023–04
  12. By: Slava Mikhed; Sahil Raina; Barry Scholnick; Man Zhang
    Abstract: We study how forcing financially distressed consumer debtors to repay a larger fraction of debt can lead them to misreport data fraudulently. Using a plausibly exogenous policy change that required debtors to increase repayment to creditors, we document that debtors manipulated data to avoid higher repayment. Consistent with deliberate fraud, data manipulators traveled farther to find more lenient insolvency professionals who, historically, approved more potentially fraudulent filings. Finally, we find that those debtors who misreported income had a lower probability of default on their debt repayment plans, consistent with having access to hidden income.
    Keywords: consumer credit; fraud; data misreporting; financial distress; default
    JEL: G21 G51 D82 D86
    Date: 2022–10–26
  13. By: Vitaly Meursault; Daniel Moulton; Larry Santucci; Nathan Schor
    Abstract: Modeling advances create credit scores that predict default better overall, but raise concerns about their effect on protected groups. Focusing on low- and moderate-income (LMI) areas, we use an approach from the Fairness in Machine Learning literature — fairness constraints via group-specific prediction thresholds — and show that gaps in true positive rates (% of non-defaulters identified by the model as such) can be significantly reduced if separate thresholds can be chosen for non-LMI and LMI tracts. However, the reduction isn’t free as more defaulters are classified as good risks, potentially affecting both consumers’ welfare and lenders’ profits. The trade-offs become more favorable if the introduction of fairness constraints is paired with the introduction of more sophisticated models, suggesting a way forward. Overall, our results highlight the potential benefits of explicitly considering sensitive attributes in the design of loan approval policies and the potential benefits of output-based approaches to fairness in lending.
    Keywords: Credit Scores; Group Disparities; Machine Learning; Fairness
    JEL: G51 C38 C53
    Date: 2022–11–21
  14. By: Breen, Casey; Seltzer, Nathan (University of California, Berkeley)
    Abstract: How accurately can age of death be predicted using basic sociodemographic characteristics? We test this question using a large-scale administrative dataset combining the complete count 1940 Census with Social Security death records. We fit eight machine learning algorithms using 35 sociodemographic predictors to generate individual-level predictions of age of death for birth cohorts born at the beginning of the 20th century. We find that none of these algorithms are able to explain more than 1.5% of the variation in age of death. Our results suggest mortality is inherently unpredictable and underscore the challenges of using algorithms to predict major life outcomes.
    Date: 2023–04–08

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.