Value-at-Risk Models Research Articles

Banking Risk in Selected MENA Countries

This study examines the influence of bank-specific variables on the individual risk of 58 banks in ten MENA countries over the period 2011-2019. Firstly, investigating the correlations among the banks’ stock returns depicts that the banks with the highest correlations are in Saudi Arabia, the United Arab Emirates, and Qatar, either domestically or across countries. Then, the individual bank risk ranking for the entire sample based on estimated historical Value-at-Risk (VaR) and Estimated Shortfall (ES) shows that the corresponding positions of banks according to their riskiness differ slightly. Noticeably, the National Bank of Fujairah in the United Arab Emirates has the highest idiosyncratic risk level in terms of both risk measures. We lastly conducted fixed and random effects panel regression models to examine the impact of bank-specific balance sheet data and macroeconomic variables on bank risk levels captured by VaR and ES. The whole sample comprises publicly listed banks in 10 countries, which were further divided into 2 sub-samples for the Gulf Cooperation Council (GCC) region and Mediterranean Partner Countries (MPCs). The outcomes of the aggregate sample suggest that lower leverage, profitability, and economic growth may exacerbate idiosyncratic risk. Results also demonstrate that strengthening stability and regulatory capital positions would lower banking risk. Considering the GCC sub-sample for VaR and ES models, we found that both risk measures typically increase with greater liquidity.

Estimating stock pledge rate using VaR and modified ES model

ABSTRACT This study mainly focuses on the reasonable determination of the stock pledge rate in the A-share market. Based on the Value-at-Risk (VaR) and modified Expected Shortfall (ES) models, 137 sample stocks were used to measure the pledge rate of stocks. The breakdown times and breakdown probability were used to verify the validity of the two models. Firstly, the results indicate that the adjusted breakdown probability calculated by the two models is less than 5%, the two models are highly reliable in measuring the stock pledge rate. Secondly, the stock pledge rate measured by the modified ES model is more effective compared with the VaR model. Finally, the prediction results of modified ES are still robust under different warning lines and liquidation lines.

Does the Value-at-Risk legal framework lead to inaccurate and procyclical risk estimations? Empirical Evidence from the EU countries.

This analysis tests whether the quantitative requirements of the law (Basel and Committee of European Securities Regulators) regarding the Value at Risk (VaR) framework may lead to inaccurate and procyclical VaR estimations. We apply two of the most popular VaR models, the Historical (HVaR) and the Exponential Weighted Moving Average (EWMA VaR) models, to a wide sample of 13 European Indices during the period 2002-2019. The empirical evidence confirms our assumptions that the legal framework in many cases leads to inaccurate and procyclical VaR estimations. Moreover, we show that the limitation on the required data inputs does not really contribute to a more stable financial environment. Further, we show that the current framework does not examine the procyclicality issue. The evidence in this study shows that the current legal framework needs some reforms: (a) the guideline on the minimum number of data inputs for the VaR estimations should be removed, taking provided that the accuracy of the applied VaR model is often evaluated, and (b) the current backtesting procedure does not examine whether VaR estimations are representative of the financial conditions. An additional backtesting procedure at a lower that the 99% confidence level could resolve this issue.

Value-at-Risk forecasting: A hybrid ensemble learning GARCH-LSTM based approach

This study proposes a new hybrid model that combines LSTM and BiLSTM neural networks with GARCH type model forecasts using an ensemble approach to forecast volatility for one-day ahead 95% and 99% Value-at-Risk (VaR) estimates using the Parametric (PAR) and Filtered Historical Simulation (FHS) method. The forecasting abilities of the standard GARCH (GARCH), exponential GARCH (eGARCH), and threshold GARCH (tGARCH) models are combined with the LSTM networks to capture different characteristics of the underlying volatility. We evaluate the model using log returns on Crude Oil during two periods of extreme volatility: the 2007-09 Financial Crisis and the Covid Recession of 2020–21. The performance of hybrid models is compared against several traditional VaR methods like the Historical Simulation, Bootstrap, Age weighted method, and the volatility-based VaR models using the GARCH, LSTM, and BiLSTM model forecasts. The unconditional and conditional coverage tests and a combination of regulator and firm loss functions are used to evaluate the quality of VaR forecasts. We find a significant improvement in the quality and accuracy of the VaR forecasts of the hybrid models over all the other models across all loss functions and coverage tests. The FHS-BiLSTM-HYBRID, a proposed FHS-based hybrid model, combining the BiLSTM model with three GARCH-type models, is the best performing, with the lowest values for both loss functions. The traditional and GARCH-type models do not efficiently model volatility during the crisis periods resulting in poor VaR forecasts. The FHS consistently performs as the best method for generating VaR compared to all other approaches.

Estimating tail-risk using semiparametric conditional variance with an application to meme stocks

In this paper, we propose using Mishra, Su, Ullah’s (2010) semiparametric variance to estimate Value at Risk (VaR) and Expected Shortfall (ES). Although the variance estimate is established in the literature, it has not been applied to VaR and ES estimation. Here the returns’ variance is estimated using Mishra, Su, Ullah’s (2010) conditional semiparametric estimator, and the standardized residuals’ distribution is fitted nonparametrically. In order to reduce possible misspecification bias, the proposed estimators decouple the assumption of the returns’ distribution and the variance estimation. Empirical and simulated data are used to compare the performance of the new estimators against existing parametric and nonparametric VaR and ES models, both conditional and unconditional. The estimators are further applied to daily returns of certain meme stocks to estimate tail risk and test the performance of the estimators during periods of extreme volatility. Compared to the models studied, the proposed conditional, semiparametric VaR model produces fewer violations, and violations without a recognizable pattern - upholding the regulatory requirements. The expected shortfall estimated by the conditional, semiparametric model is also closest to the observed mean of the violations.

Volatility spillover effect between Pakistan and Shanghai Stock Exchanges using copula and dynamic conditional correlation model

PurposeBecause of the growing financial market integration, China’s stock market’s volatility spillover effect has gradually increased. Traditional strategies do not capture stock volatility in dependence and dynamic conditions. Therefore, this study aims to find an effective stochastic model to predict the volatility spillover effect in the dynamic stock markets.Design/methodology/approachTo assess the time-varying dynamics and volatility spillover, this study has used an integrated approach of dynamic conditional correlation model, copula and extreme-value theory. A daily log-returns of three leading indices of Pakistan Stock Exchange (PSX) and Shanghai Stock Exchange (SSE) from the period of 2009 to 2019 is used in the modeling of value-at-risk (VaR) for volatility estimation. The Student’s t copula has been selected based on maximum likelihood estimation and Akaike’s information criteria values of all the copulas using the goodness-of-fit test.FindingsThe model results show stronger dependency between all major portfolios of PSX and SSE, with the parametric value of 0.98. Subsequently, the results of dependence structure positively estimate the spillover effect of SSE over PSX. Furthermore, the back-testing results show that the VaR model performs well at 99% and 95% levels of confidence and gives more accurate estimates upon the maximum level of confidence.Practical implicationsThis study is helpful for the investment managers to manage the risk associated to portfolios under dependence conditions. Moreover, this study is also helpful for the researchers in the field of financial risk management who are trying to improve the returns by addressing the issues of volatility estimations.Originality/valueThis study contributes to the body of knowledge by providing a practical model to manage the volatility spillover effect in dependence conditions between as well as across the financial markets.

Backtesting the evaluation of Value-at-Risk methods for exchange rates

PurposeSmall- and medium-sized enterprises can be highly affected by losses caused by exchange rate changes. The aim of this paper was to find the optimal Value-at-Risk (VaR) method for estimating future exchange rate losses within one year.Design/methodology/approachThe analysis focuses on five VaR methods, some of them traditional and some of them more up to date with integrated EVT or GARCH. The analysis of VaR methods was concentrated on a time horizon (1–12 months), overestimation predictions and six scenarios based on trends and variability of exchange rates. This study used three currency pairs EUR/CZK, EUR/USD and EUR/JPY for backtesting.FindingsIn compliance with the backtesting results, the parametric VaR with random walk has been chosen, despite its shortcomings, as the most accurate for estimating future losses in a medium-term period. The Nonparametric VaR confirmed insensitivity to the current exchange rate development. The EVT-based methods showed overconservatism (overestimation predictions). Every parametric or semiparametric method revealed a severe increase of liberality with increasing time.Research limitations/implicationsThis research is limited to the analysis of suitable VaR models in a long- and short-run period without using artificial intelligence.Practical implicationsThe result of this paper is the choice of a proper VaR method for the online application for estimating the future exchange rate for enterprises.Originality/valueThe orientation of medium-term period makes the research original and useful for small- and medium-sized enterprises.

DeepVaR: a framework for portfolio risk assessment leveraging probabilistic deep neural networks

Determining and minimizing risk exposure pose one of the biggest challenges in the financial industry as an environment with multiple factors that affect (non-)identified risks and the corresponding decisions. Various estimation metrics are utilized towards robust and efficient risk management frameworks, with the most prevalent among them being the Value at Risk (VaR). VaR is a valuable risk-assessment approach, which offers traders, investors, and financial institutions information regarding risk estimations and potential investment insights. VaR has been adopted by the financial industry for decades, but the generated predictions lack efficiency in times of economic turmoil such as the 2008 global financial crisis and the COVID-19 pandemic, which in turn affects the respective decisions. To address this challenge, a variety of well-established variations of VaR models are exploited by the financial community, including data-driven and data analytics models. In this context, this paper introduces a probabilistic deep learning approach, leveraging time-series forecasting techniques with high potential of monitoring the risk of a given portfolio in a quite efficient way. The proposed approach has been evaluated and compared to the most prominent methods of VaR calculation, yielding promising results for VaR 99% for forex-based portfolios.

Value-at-risk in the presence of asset price bubbles

ABSTRACT In this study, we respond to the criticism that the value-at-risk (VaR) measure fails during financial crises and is only applicable during periods without asset price bubbles. We propose a new dating mechanism that is based on the work of Phillips (2015) to date-stamp the origination and termination of the asset price bubbles. Our method relaxed the minimum bubble duration constraint in the original model, and the empirical application statistically identified the bubbles periods in nine stock markets (Australia, Canada, China, Germany, Spain, Hong Kong, Japan, the United Kingdom, and the United States). We choose the two most widely adopted VaR models (RiskMetrics and RiskMetrics 2006) to test the performance. Our results show that the RiskMetrics model fails in most periods, whereas the RiskMetrics 2006 performs efficiently in the periods with asset price bubbles. These results prove the criticism that all the VaR models fail during crises as invalid.

Measuring the integrated risk of China’s carbon financial market based on the copula model

Measuring the risks of the carbon financial market is of great significance for investment decision-making, risk supervision, and the healthy development of the carbon trading market. Different from previous studies based on traditional VaR (value at risk), this study measures the integrated risk of China's carbon market based on the Copula-EVT (Extreme Value Theory) -VaR model which can explore the unique strength of the copula and EVT-VaR models, of which the copula model is applied to capture the dependence between the different risk factors of carbon price volatility and macroeconomic fluctuation, while the EVT-VaR is used to explore the risk value. The empirical results show that the traditional VaR that only considers a single risk factor from carbon price volatility is likely to overestimate the risk. In addition, compared with other methods that do not consider the interdependence between risk factors, using the copula function to measure the carbon market integration risk is more effective, and backtesting also confirms this conclusion. This paper provides a specific reference for carbon emission companies to participate in the carbon market. It provides a theoretical basis for the supervision of the risk management of the carbon market.

Forecasting Startup Return using Artificial Intelligence Methods and Econometric Models and Portfolio Optimization Using VaR and C-VaR

In this paper, we have tried to study the main role of startups in economy, their characteristics, main goals and etc. The main goal of article is prediction of startup's return using artificial intelligence methods such as genetic algorithm (GA) and artificial neural network (ANN). Some global indices such as S&P500, DJAI, and economic indicators such as 10 years Treasury yield, Wilshire 5000 Total Market Full Cap Index along with some other special indicators in startups like team, idea, timing and etc. are used as input variables. GA is used as feature selection and finding the most important variables. ANN is used as an optimization model and prediction of startup's returns. We used econometric models such as regression analysis. We have estimated Value at risk (VaR) and Conditional Value at risk (C-VAR) for considered portfolios including three startups (public company) such as Dropbox, Inc. (DBX), Scout24 SE (G24.DE) and TIE.AS and optimal portfolio formation. The results show that AI based methods are more powerful in prediction of startup's return. On the other hand, VaR and C-VaR models are very beneficial approach in minimizing risk and maximizing return.

Equity Price Risk of Commercial Banks in India

This study is directed at gauging the equity price risk of the Indian commercial banks for the period 2003–2020. Parametric value-at-risk (VaR) is employed to estimate the downside risk. Further, the univariate exponential generalized auto regressive conditional heteroskedasticity (EGARCH) model is also used to find out the existence of stylised aspects of volatility. The outcomes point towards the existence of volatility clustering, persistence and asymmetry, but differ from bank to bank. Furthermore, the parametric VaR model that assumes normal distribution and student’s t-distribution is not found to be an accurate model for all the banks. Tail risk is also found to be significant, and thus, justifies the Basel Committee’s decision to shift towards an expected shortfall. However, these conventional VaR models should be supplemented by internal models, taking into consideration, bank-specific characteristics. JEL: G01, G15, I15, G17, G28

Distributional Uncertainty of the Financial Time Series Measured by $G$-Expectation

Based on the law of large numbers and the central limit theorem under nonlinear expectation, we introduce a new method of using ${G}$-normal distribution to measure financial risks. Applying max-mean estimators and a small windows method, we establish autoregressive models to determine the parameters of ${G}$-normal distribution, i.e., the return, maximal, and minimal volatilities of the time series. Utilizing the value at risk (VaR) predictor model under ${G}$-normal distribution, we show that the ${G}$-VaR model gives an excellent performance in predicting the VaR for a benchmark dataset comparing to many well-known VaR predictors.

Value-at-risk (VAR) estimation and backtesting during COVID-19: Empirical analysis based on BRICS and US stock markets

Value-at-risk (VaR) is the most common and widely used risk measure that enterprises, particularly major banking corporations and investment bank firms employ in their risk mitigation processes. The purpose of this study is to investigate the value-at-risk (VaR) estimation models and their predictive performance by applying a series of backtesting methods on BRICS (Brazil, Russia, India, China, South Africa) and US stock market indices. The study employs three different VaR estimation models, namely normal (N), historical (HS), exponential weighted moving average (EMWA) procedures, and eight backtesting models. The empirical analysis is conducted during three different periods: overall period (2006–2021), global financial crisis (GFC) period (2008–2009), and COVID-19 period (2020–2021). The results show that the EMWA model performs better compared to N and HS estimation models for all the six stock market indices during overall and crisis sample periods. The results found that VaR models perform poorly during crisis periods like GFC and COVID-19 compared to the overall sample period. Furthermore, the study result shows that the predictive accuracy of VaR methods is weak during the COVID-19 era when compared to the GFC period.

Research on Financial Market Risks Based on VaR Model

With the continuous development of the Internet financial industry, its impact on people's daily life is growing. Under the influence of the information technology and the financial innovation, the volatility of the financial market has been significantly enhanced, and the financial risk has become increasingly serious. The COVID-19 in 2020 still has a profound impact on the global financial market. The reasonable measurement of the financial risks is the most important step in the financial risk management. Based on the sample analysis of the Standard & Poor's 500 Index from January 3, 2013 to June 30, 2020, this paper measures the risks by analyzing and calculating the value at risk (VaR) of the sample data by different methods. This paper mainly establishes the ARMA model, the GARCH model based on bayese statistics, and the POT model based on the extreme value theory, and compares and analyzes the VaR values obtained by the three models. Finally, the effectiveness of VaR is tested by VaR backtracking test, and the advantages and disadvantages of the methods are compared and evaluated.

Evaluation of backtesting on risk models based on data envelopment analysis

In this study, different value-at-risk (VaR) models, which are used to measure market risk, are analyzed under different estimation approaches and backtested with an alternative strategy. The methodologies examined include filtered historical simulation, extreme value theory, Monte Carlo simulation and historical simulation. Autoregressive-moving-average and generalized-autoregressive-conditional-heteroscedasticity models are used to estimate VaR. Selected VaR functions, marginal distributions and different horizons are combined over a set of extreme probability levels using the time series of the Financial Times Stock Exchange 100 index. Data envelopment analysis, which investigates the efficiency of VaR models using a number of different parameters, is carried out in lieu of standard backtesting techniques. This study shows that, for short horizons, some approaches underestimate VaR. However, a sufficient number of models present violation estimates that almost converge to the desired ones. Surprisingly, aside from historical simulation and some extreme value theory models, overlapping returns tend to yield conservative ten-day VaR estimations for most models; in cases of nonoverlapping returns, the results are satisfactory.

COPULA FRANK UNTUK PERHITUNGAN VALUE AT RISK PORTOFOLIO BIVARIAT PADA MODEL EXPONENTIAL GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTICITY

Stocks are one type of investment that promises return for investors but often carries a high risk. Value at Risk (VaR) is a measuring tool that can calculate the amount of the worst loss that occurs in a stock portfolio with a certain level of confidence and within a certain time period. In general, financial data have a high volatility value, which causes the residuals are not normally distributed. ARCH/GARCH modoel is used to solve the heteroscedasticity problem. If the data also have an asymmetric effect, it is modelled with Exponential GARCH model. Copula-Frank is part of the Archimedian copula which is used to solve empirical cases. The data on this study were BBCA and KLBF stock price return data in the observation period 30 December 2011 – 6 December 2019. Furthermore, to test the validity of the VaR model, a backtesting test will be carried out using the Kupiec Test. The results showed that the best model used for BBCA stocks was ARIMA (1,0,1) EGARCH (1,1) and for KLBF stocks was ARIMA (1,0,1) EGARCH (1,2). The amount of risk with a 95% confidence level used a combination of the EGARCH and Copula-Frank models was 2.233% of today's investment. Based on the backtesting test used the Kupiec Test, the VaR model of the portfolio obtained was declared valid.

Estimating Model Risk of VaR under Different Approaches: Study on European Banks

The objective of this research is to estimate the model risk, represented as precision, and the accuracy of the Value at Risk (VaR) measure, under three different approaches: historical simulation (HS), Monte Carlo (MC), and generalized ARCH (GARCH). In this work, to analyze the VaR model, the accuracy and precision were used. Estimation of the accuracy and precision was done under the three approaches for four European banks at 95 and 99% confidence levels. The percentage crossings and Kupiec POF were used to judge the model accuracy, whereas the ratio of the maximum and minimum VaR estimates, and the spread between the maximum and minimum VaR estimates were used to estimate the model risk. This was achieved by changing input parameters, specifically, the estimation time window (125, 250, 500 days). Implications/Recommendations: The accuracy alone is not sufficient to evaluate a model and precision is also required. The temporal evolution of the precision metrics showed that the VaR approaches were inconsistent under different market conditions. This article focuses on the accuracy and precision concepts applied to estimate model risk of the Value at Risk (VaR). VaR is the foundation for sophisticated risk metrics, including systemic risk measures like Marginal Expected Shortfall and Delta Conditional Value at Risk. Thus, understanding the risk associated with the use of VaR is crucial for finance practitioners.

The Accuracy of Risk Measurement Models on Bitcoin Market during COVID-19 Pandemic

Since late 2019, during one of the largest pandemics in history, COVID-19, global economic recession has continued. Therefore, investors seek an alternative investment that generates profits during this financially risky situation. Cryptocurrency, such as Bitcoin, has become a new currency tool for speculators and investors, and it is expected to be used in future exchanges. Therefore, this paper uses a Value at Risk (VaR) model to measure the risk of investment in Bitcoin. In this paper, we showed the results of the predicted daily loss of investment by using the historical simulation VaR model, the delta-normal VaR model, and the Monte Carlo simulation VaR model with the confidence levels of 99%, 95%, and 90%. This paper displayed backtesting methods to investigate the accuracy of VaR models, which consisted of the Kupiec’s POF and the Kupiec’s TUFF statistical testing results. Finally, Christoffersen’s independence test and Christoffersen’s interval forecasts evaluation showed effectiveness in the predictions for the robustness of VaR models for each confidence level.

Value-at-risk predictive performance: a comparison between the CaViaR and GARCH models for the MILA and ASEAN-5 stock markets

PurposeThis paper tests the accuracies of the models that predict the Value-at-Risk (VaR) for the Market Integrated Latin America (MILA) and Association of Southeast Asian Nations (ASEAN) emerging stock markets during crisis periods.Design/methodology/approachMany VaR estimation models have been presented in the literature. In this paper, the VaR is estimated using the Generalized Autoregressive Conditional Heteroskedasticity, EGARCH and GJR-GARCH models under normal, skewed-normal, Student-t and skewed-Student-t distributional assumptions and compared with the predictive performance of the Conditional Autoregressive Value-at-Risk (CaViaR) considering the four alternative specifications proposed by Engle and Manganelli (2004).FindingsThe results support the robustness of the CaViaR model in out-sample VaR forecasting for the MILA and ASEAN-5 emerging stock markets in crisis periods. This evidence is based on the results of the backtesting approach that analyzed the predictive performance of the models according to their accuracy.Originality/valueAn important issue in market risk is the inaccurate estimation of risk since different VaR models lead to different risk measures, which means that there is not yet an accepted method for all situations and markets. In particular, quantifying and forecasting the risk for the MILA and ASEAN-5 stock markets is crucial for evaluating global market risk since the MILA is the biggest stock exchange in Latin America and the ASEAN region accounted for 11% of the total global foreign direct investment inflows in 2014. Furthermore, according to the Asian Development Bank, this region is projected to average 7% annual growth by 2025.