Market Risk Measures Research Articles

Encoded Value-at-Risk: A Predictive Machine for Financial Risk Management

Measuring risk is at the center of modern financial risk management. As the world economy is becoming more complex and standard modeling assumptions are violated, the advanced artificial intelligence solutions may provide the right tools to analyze the global market. In this paper, we provide a novel approach for measuring market risk called Encoded Value-at-Risk (Encoded VaR), which is based on a type of artificial neural network, called Variational Auto-encoders (VAEs). Encoded VaR is a generative model which can be used to reproduce market scenarios from a range of historical cross-sectional stock returns, while increasing the signal-to-noise ratio present in the financial data, and learning the dependency structure of the market without any assumptions about the joint distribution of stock returns. We compare Encoded VaR out-of-sample results with eleven other methods and show that it is competitive to many other well-known VaR algorithms presented in the literature.

Risk Early Warning Research on China’s Futures Company

ABSTRACT Having effective and reliable risk management is essential for the development of futures trading companies in China. Research analyzing early warnings on related risks for futures trading companies in China have important theoretical and empirical value. In this paper, we take the period during which fluctuation in extreme market risk occurred as the verification period and design overall risk indicators and equations to measure market risk for futures trading companies. We built an early risk warning model using extreme learning machine technology. We tested our model’s validity using statistics from China’s futures market. Empirical evidence shows that our model is more accurate than models based on the support vector machine, logistic regression, and the back-propagation neural network.

Backtesting Marginal Expected Shortfall and Related Systemic Risk Measures

This paper proposes an original approach for backtesting systemic risk measures. This backtesting approach makes it possible to assess the systemic risk measure forecasts used to identify the financial institutions that contribute the most to the overall risk in the financial system. Our procedure is based on simple tests similar to those generally used to backtest the standard market risk measures such as value-at-risk or expected shortfall. We introduce a concept of violation associated with the marginal expected shortfall (MES), and we define unconditional coverage and independence tests for these violations. We can generalize these tests to any MES-based systemic risk measures such as SES, SRISK, or ∆CoVaR. We study their asymptotic properties in the presence of estimation risk and investigate their finite sample performance via Monte Carlo simulations. An empirical application to a panel of U.S. financial institutions is conducted to assess the validity of MES, SRISK, and ∆CoVaR forecasts issued from a GARCH-DCC model. Our results show that this model provides valid forecasts for MES and SRISK when considering a medium-term horizon. Finally, we propose an early warning system indicator for future systemic crises deduced from these backtests. Our indicator quantifies how much is the measurement error issued by a systemic risk forecast at a given point in time which can serve for the early detection of global market reversals.

Long memory or structural break? Empirical evidences from index volatility in stock market

PurposeThe purpose of this paper is to explore whether stock index volatility series exhibit real long memory.Design/methodology/approachThe authors employ sequential procedure to test structural break in volatility series, and use DFA and 2ELW to estimate long memory parameter for the whole samples and subsamples, and further apply adaptive FIGARCH (AFIGARCH) to describe long memory and structural break.FindingsThe empirical results show that stock index volatility series are characterized by long memory and structural break, and therefore it is appropriate to use AFIGARCH to model stock index volatility process.Originality/valueThis study empirically investigates the properties of long memory and structural break in stock index volatility series. The conclusion has a certain reference value for understanding the properties of long memory and structural break in volatility series for academic researchers, market participants and policy makers, and for modeling and forecasting future volatility, testing market efficiency, pricing financial assets, constructing quantitative investment strategy and measuring market risk.

The impact of liquidity on portfolio value-at-risk forecasts

ABSTRACTHistorical crisis events have highlighted the insufficiency of Value-at-Risk (VaR) as a measure of market risk because such metric does not take liquidity into account. Unlike previous studies analyzing with only a single asset, we examine the impact of liquidity on computing VaR forecasts from a portfolio level. To this end, we use multivariate GARCH-t and GJR-GARCH-t models, as compared with univariate models, to seize the liquidity property embedded in individual stock returns and evaluate their accuracy and efficiency in computing VaR forecasts for portfolios with different liquidity levels.The empirical results indicate that computing portfolio VaR forecasts with multivariate models outperform the univariate models for full and subsample periods in terms of accuracy and efficiency evaluations, in particular for less-liquid portfolios. These results suggest the importance of liquidity in computing portfolio VaR forecasts. Ignorance of the impact of liquidity in computing portfolio VaR forecasts might result in inadequate coverage and insufficient market risk capital requirements.

Estimating Value-at-Risk and Expected Shortfall using the intraday low and range data

Value-at-Risk (VaR) is a popular measure of market risk. To convey information regarding potential exceedances beyond the VaR, Expected Shortfall (ES) has become the risk measure for trading book bank regulation. However, the estimation of VaR and ES is challenging, as it requires the estimation of the tail behaviour of daily returns. In this paper, we take advantage of recent research that develops joint scoring functions for VaR and ES. Using these functions, we present a novel approach to estimating the two risk measures based on intraday data. We focus on the intraday range, which is the difference between the highest and lowest intraday log prices. In contrast to intraday observations, the intraday low and high are widely available for many financial assets. To alleviate the challenge of modelling extreme risk measures, we propose the use of the intraday low series. We draw on a theoretical result for Brownian motion to show that a quantile of the daily returns can be estimated as the product of a constant term and a less extreme quantile of the intraday low returns, which we define as the difference between the lowest log price of the day and the log closing price of the previous day. In view of this, we use estimates of the VaR and ES of the intraday low returns to estimate the VaR and ES of the daily returns. We provide empirical support for the new proposals using data for five stock indices and five individual stocks.

Оценяване на портфейлния пазарен риск чрез метода „стойност под риск“ (VaR) – историческа симулация

One of the main VaR methods on theoretical aspect – Historical Simulation to Portfolio is explained in this article. Portfolio market risk measurement is carried out towards the shares of the particular companies – The Procter & Gamble Company (PG), Toyota Motor Corporation (TM) and Nokia Corporation (NOK).

Dynamic Probabilistic Forecasting with Uncertainty

We introduce a dynamical model for the time evolution of probability density functions incorporating uncertainty in the parameters. The uncertainty follows stochastic processes, thereby defining a new class of stochastic processes with values in the space of probability densities. The purpose is to quantify uncertainty that can be used for probabilistic forecasting. Starting from a set of traded prices of equity indices such as FTSEMIB, FTSE100 and S&P500 we do some empirical studies. We apply our dynamic probabilistic forecasting to option pricing, where our proposed notion of model uncertainty reduces to uncertainty on future volatility. A distribution of option prices follows, reflecting the uncertainty on the distribution of the underlying prices. We associate measures of model uncertainty of prices in the context of Cont (2006). As a further application we look at the Sharpe ratio and the VaR measure of market risk as well, proposing some decision rules for investors, regulators and risk managers.

Integrated measurement of liquidity risk and market risk of company bonds based on the optimal Copula model

The bond market is an important part of the capital market, reflecting the debtor-creditor relationship. Correspondingly, the P2P network lending platform, which plays a vital role in emerging Internet Finance, represents the same relationship. In both markets, the risks in investment and financing channels are complex and diverse, including liquidity risk, market risk, tax risk and so on. All the risks do not exist alone, performed as an integrated risk. This paper establishes an index for measuring corporate bonds’ liquidity, by using a Copula-GARCH approach and generating empirical distribution to integrate the liquidity risk and market risk of corporate bonds. Particularly, according to the Likelihood function test results, t-Copula is the optimum Copula function. The model can also be applied to measure the integrated risk of the P2P network lending platform after improvement.

Evaluasi Kualitas Pengungkapan Value at Risk Perbankan Indonesia

Market risk measurement of bank investment portfolios is a still problem not only among practitioners, but also among academicians. The accuracy and quality of market risk disclosures are important issues because transparency of the bank risk level encourages market control in the form of market discipline and it also improve the quality of risk management carried out internally by the bank. This research measures the quality of Value at Risk disclosures carried out by Indonesian banks. The accuracy of Value at Risk in this research is measured from the Value at Risk component which contains information of yield volatility of bank trading treasury activities. To measure Value at Risk disclosure, this research runs various methods of Value at Risk measurement. This research shows Historical Simulation is a Value at Risk method that is most widely used by Indonesia banks. The empirical test results show that the Value at Risk parametric method using asymmetric volatility have better quality than the Value at Risk Historical Simulation method. This research shows that Value at Risk as measured by Historical Simulation method contains the least information of bank trading treasury yields.
 Keywords: value at risk; disclosure; market risk; volatility

Absorption rate as a system risk measurement tool: evidence from the Viet Nam stock market

System risk is one of the problems concerned by many stock market researchers. Many different indicators have been used: the average price index Passcher, Laspeyres or Fisher. These indicators reflect the average price of stocks or a basket of representative stocks in the m arket. The models predicting the prices of these indexes are the measure of market risk. Recently, especially after the major financial crises, the plunge of the stock market indexes has been s een. There are two issues here: Firstly, whether a market index fully reflects systemic r isk. Secondly, any state of market risk implicit breakdowns. Mark Kritzman et al., 2010 proposed index of Absorption Rate as a system risk measurement tool. Research results of the authors and some other studies show that: 1. The sharp decline of the US stock market against the soaring rate of absorption; 2. Stocks devalued significantly after the rate of absorption increased and then p lummeted; 3 . Absorption rate is a leading indicator of the US housing market bubble; 4. Increased absorption rate has a system of market turmoil; 5. The time of major financial crisis coincided with a large change of this rate; 6. Absorption rate contains a large proportion of information about structural models and complex calculations of financial s pread. This article introduces and tests the use of absorption rate to analyze the volatility of the Vietnam stock market. The analysis will focus on a number of periods with different market fluctuations. Experiment uses absorption rate index for a pricing model.

PENERAPAN MANAJEMEN RESIKO BANK, TATA KELOLA PERUSAHAAN DAN KINERJA PERUSAHAAN PERBANKAN INDONESIA

Bank as one of the financial institutions in Indonesia is demanded by its owners and shareholders to have good performance in order to continuously increase the value of the company. In order to improve performance, companies must be able to analyze the risks that might occur by implementing risk management. However, good risk management is not adequate to describe the good performance of banks if the banking sector has not been well implemented the GCG. This study aims to examine the effect of risk management and Good Corporate Governance (GCG) on company performance. Research conducted on companies from the banking sector included in 50 top companies list with highest CG score based on the IICD version in 2017. Risk management in this study is measured by four ratios, namely the NPL ratio to measure credit risk, NIM to measure market risk, LDR to measure risk liquidity and BOPO to measure operational risk. GCG in this study is measured by the results of GCG implementation assessment based on the ASEAN CG Scorecard. ROA and Tobin's Q, measure the company's performance as the dependent variable in this study. The results showed that only NPL, NIM and BOPO had a significant effect on company performance that was proxied by ROA and only LDR, BOPO and GCG that had a significant effect on company performance, which was proxied with Tobin's Q.

Market Risk and Financial Performance of Non-Financial Companies Listed on the Moroccan Stock Exchange

This study examines the effect of market risk on the financial performance of 31 non-financial companies listed on the Casablanca Stock Exchange (CSE) over the period 2000–2016. We utilized three alternative variables to assess financial performance, namely, the return on assets, the return on equity and the profit margin. We used the degree of financial leverage, the book-to-market ratio, and the gearing ratio as the indicators of market risk. Then, we employed the pooled OLS model, the fixed effects model, the random effects model, the difference-GMM and the system-GMM models. The results show that the different measures of market risk have significant negative influences on the companies’ financial performance. The elasticities are greater following the degree of financial leverage compared with the book-to-market ratio and the gearing ratio. In most cases, the firm’s age, the cash holdings ratio, the firm’s size, the debt-to-assets ratio, and the tangibility ratio have positive effects on financial performance, whereas the debt-to-income ratio and the stock turnover hurt the performance of these non-financial companies. Therefore, decision-makers and managers should mitigate market risk through appropriate strategies of risk management, such as derivatives and insurance techniques.

Neural Networks and Arbitrage in the VIX – A Deep Learning Approach for the VIX

The Chicago Board Options Exchange (CBOE) Volatility Index, often referred to as VIX Volatility Index (VIX), is considered by many market participants as a common measure of market risk and investors' sentiment. It is also sometimes called the fear index. In general, the VIX represents the market's expectation of the 30-day-ahead looking implied volatility obtained from real-time prices of options on the S&P 500 index. Over the last few years, many claims about possible VIX manipulations have been brought up by market participants. The increased attention on the VIX has been revived again by unusual trading patterns, which were observed on the market, on February 5 and April 18, 2018. While smaller deviations between implied and realized volatility are a well-known stylized fact of financial markets, large, time-varying differences are also frequently observed throughout the day. In theory, such large deviations might lead to arbitrage opportunities on the VIX market. However, it is hard to exploit as the potential replication strategy requires buying several hundred out-of-the-money (put and call) options on the S&P 500 index. In addition, the potential list of options used for building the replication strategy constantly changes due to underlying price movements, making it difficult to implement it in real-time. Finally, in most cases, the theoretical replication strategy involves high transaction costs which are driven by illiquid options. This paper discusses a novel approach to replicating and predicting the VIX by using just a subset of the most liquid options. The presented approach is based on a recurrent neural network, more precisely on a long short-term model (LSTM) and it uses intraday data of S&P 500 options and the VIX. The results can be used to find a much more cost-efficient way of replicating the VIX and exploiting any arbitrage opportunities. To the best of the authors' knowledge, this the first paper, that describes a new methodology on how to replicate the VIX (to potentially exploit arbitrage opportunities using VIX futures) and applies most recently developed machine learning models to intraday data of S&P 500 options and the VIX. The presented results are supposed to shed more light on the ongoing discussions about possible market manipulations, help other investors to better understand the market and support regulators to investigate market inefficiencies.

Modelling Risk on the Egyptian Stock Market: Evidence from a Markov-Regime Switching GARCH Process

This research aims at evaluating among market risk measures to equity exposures on the Egyptian stock market, while utilising a variety of parametric and non-parametric methods to estimating volatility dynamics. Historical Simulation, EWMA (RiskMetrics), GARCH, GJR-GARCH, and Markov-Regime switching GARCH models are empirically estimated. Value at Risk and Conditional Value at Risk measures are backtested in order to evaluate among the alternative models. Results indicate the superiority of asymmetric GARCH models when combined with a Markov-Regime switching process in quantifying market risk - as is evident from the results of the backtests - which have been performed in accordance with the current regulatory demands. Implications are important to regulators and practitioners.

Comparing Different Systemic Risk Measures for European Banking System

This research examines and compares the performances in terms of systemic risk ranking for three different systemic risk metrics based on daily frequency publicly available data, specifically: Marginal Expected Shortfall (ES), Component Expected Shortfall (CES) and Delta Conditional Value-at-Risk (ΔCoVaR). We compute ΔCoVaR, MES and CES by utilizing EVT principles for modelling marginal distributions and Student’s t copula for describing the dependence structure between every bank and the banking system. Our objective is to attest whether different systemic risk metrics detect the same banks as systemically dangerous institutions with refer to a sample of European banks over the time span 2004-2015. For each bank in the sample we also calculate three traditional market risk measures, like Market VaR, Sharpe’s beta and the correlation between every bank and the banking system (European STOXX 600 Banks Index). Another aim is to explore the existence of a link among systemic risk measures and traditional risk metrics. In addition, the classification results obtained by the different risk metrics are compared with the ranking in terms of systemic riskiness (for European banks) calculated by Financial Stability Board (2015) using end-2014 data and collected in its list of Global Systemically Important Banks (G-SIBs). With refer to the entire sample period, we find a good coherence of ranking results among the three different systemic risk metrics, in particular between CES and ΔCoVaR. Moreover, we find for MES and ΔCoVaR a strong linkage with beta and correlation metrics respectively. Finally, CES metric shows the highest level of concordance with the list of G-SIBs by FSB with refer to European banks.

Pomiar ryzyka rynkowego miarą wartoś​ci zagrożonej. Metoda kombinowania prognoz ​

The article discusses the measurement of market risk by Value at Risk method. Value at Risk measure is an important element of risk measurement mainly for financial institutions but can also be used by other companies. The Value at Risk is presented together with its alternative Conditional Value at Risk. The main methods of VaR estimation were divided into nonparametric, parametric and semi-parametric methods. The next part of the article presents a method of combining forecasts, which can be used in the context of forecasting Value at Risk.

Financial Companies’ Failures: Early Warning Information from Systematic and Systemic Risk Measures

Following the 2007–2008 financial crisis, advanced risk measures were proposed with the specific aim of quantifying systemic risk, since the existing systematic (market) risk measures seemed inadequate to signal the collapse of an entire financial system. The paper aims at comparing the systemic risk measures and the earlier market risk measures regarding their predictive ability toward the failure of financial companies. Focusing on the 2007–2008 period and considering 28 large US financial companies (among which nine defaulted in the period), four systematic and four systemic risk measures are used to rank the companies according to their risk and to estimate their relationship with the company’s failure through a survival Cox model. We found that the two groups of risk measures achieve similar scores in the ranking exercise, and that both show a significant effect on the time-to-default of the financial institutions. This last result appears even stronger when the Cox model uses, as covariates, the risk measures evaluated one, three and six months before. Considering this last case, the most predictive risk measures about the default risk of financial institutions were the Expected Shortfall, the Value-at-Risk, the [Formula: see text] and the [Formula: see text]. We contribute to the literature in two ways. We provide a way to compare risk measures based on their predictive ability toward a situation, the company’s failure, which is the most catastrophic event for a company. The survival model approach allows to map each risk measure in terms of probability of default over a given time horizon. We note, finally, that although focused on the Great Recession in US, the analysis can be applied to different periods and countries.

Financial risk management based on functional data analysis

Financial risk management is of great significance in modern society. The method of functional data analysis is extended to the research on financial market risk measurement, and a new research perspective and analytical tool is provided for better grasping the change law of financial market fluctuation and exploring the potential structure and dynamic changes of financial assets risk. Taking the stock market as an example, a systematic and detailed analysis of the risk measurement of China’s financial market is made, and it provides a new empirical evidence to better know and understand the risk of China’s financial market. The important ideas of functional data analysis, time series analysis and statistical algorithms are combined and applied it to the study of risk measurement in financial risk management. The empirical analysis shows that China’s stock market not only changes the average level of risk changes, but also changes the main change factors of risk changes.

On the risk spillover across the oil market, stock market, and the oil related CDS sectors: A volatility impulse response approach

Compared to Credit Default Swap (CDS) literature, this study focuses on the magnitude of volatility transmission and the risk spillover mechanism across the oil market, financial market risks, and the oil-related CDS sectors. Our dataset includes futures prices of West Texas Intermediate (WTI) and seven different measures of markets and credit risks. Four of the vast risk measures are the oil-related CDSs for auto, chemicals, natural gas, and utility sectors. In addition, three measures of the financial market risk, the one-month expected equity volatility measured by VIX, MOVE and SMOVE are included. The daily dataset covers the period from 6 January 2004 to 2 February 2016. The volatility transmission mechanism across the oil and financial markets and CDS sectors is examined using the volatility impulse response model. We evaluate the risk transmission due to several recent crisis shocks around the world and the results show complicated transmission mechanisms that spread over long periods. Among these events, the Lehman Brothers bankruptcy has destabilizing effects on all oil-related sectors. Findings also show that all oil market related shocks have significant risk transmission effects.