Hot Spots and Hedges

An empirical investigation on how portfolio risk management influences project portfolio success

The assessment and prediction of the impact of risks on the financial performance of portfolios is a very challenging task, and many portfolios in Qatar and worldwide are still suffering from cost overruns. This aspect is undeveloped in the body of literature on portfolio risk management, and very few studies have addressed this need. Therefore, organisations and portfolio managers are still looking for tools and techniques which enable them to incorporate the financial impacts of risks during the estimation of the cost and contract price of their portfolios. In this paper, a risk management-based methodology for the prediction of the cost and the financial performance of portfolios is presented and tested on real case studies based at Qatar Gas. The methodology is based on calculating the combined effect of multiple risks on the different work packages composing part the portfolio project, while considering the probabilistic occurrence of each risk. The methodology was tested on four projects in Qatar Gas and proved to be able to predict the effect of the identified risks on financial performance related to each portfolio. It also helped to prioritize the risks and identify the risks that most affected the financial performance of the portfolio and, thus, provide valuable information for particular stages of response planning. One of the limitations of the proposed methodology is that it calculates the impact of risks on the financial performance of a portfolio at a specific date, where risk impacts have a defined probabilistic distribution. However, the dynamic nature of risk attributes could be reflected by changing the values of those attributes in the risk management model of the portfolio every time the risk register is updated.

Understanding the dynamics of realized volatility is critical to effective investment management and portfolio risk management. Volatility measures can reach levels well above the median and are trending and mean reverting. Tradable volatility exposure is now available with VIX futures and exchange-traded products benchmarked to VIX futures indices. These tools are useful for modifying portfolio risk based on expected S&P 500 Index volatility rather than shifting fixed-income allocations.

The financial industry's rapid adoption of artificial intelligence (AI) for portfolio risk assessment creates a tension between predictive power and explainability—a critical concern for fiduciary obligations. This research explores the implementation of explainable AI (XAI) methodologies in portfolio risk management, comparing traditional black-box models with transparent alternatives. We evaluate LIME, SHAP, and rule-based explainers against complex neural networks and ensemble methods across diverse market conditions using a comprehensive dataset of financial instruments. Results demonstrate that XAI approaches can achieve 92.4% of black-box performance while providing interpretable insights, satisfying regulatory requirements without significant accuracy sacrifices. Our framework integrates explainability metrics with performance indicators, creating a balanced scorecard for model selection in financial contexts. This work addresses the growing demand for transparent AI in financial decision-making, offering practical guidance for portfolio managers navigating the intersection of advanced analytics and fiduciary responsibility.

Kripto varlıklar pay senetleri ve emtialar gibi geleneksel yatırım araçlarıyla karşılaştırıldığında daha az düzenleme, düşük işlem maliyetleri, merkeziyetsizlik gibi bazı avantajlara sahiptirler. Kripto varlıklar ortaya çıkışlarından günümüze kadar fiyat, hacim ve değer bakımından artarak portföylerde kendilerine yer edinmeye başlamışlardır. Kripto varlıkların geleneksel yatırım araçlarıyla olan ilişkileri portföy yönetimi açısından sonuçlar ortaya çıkarabilir. Bu çalışmada bitcoin ile altın, petrol, doğal gaz ve emtia endeksinden oluşan emtialar arasındaki volatilite yayılımları incelenmiştir. Çalışmada 24 Ağustos 2016 – 13 Ocak 2023 dönemine ait günlük veriler varyansta nedensellik ve Lu, Hong, Wang, Lai ve Liu (2014) tarafından geliştirilen zamanla değişen varyansta nedensellik testiyle incelenmiştir. Çalışmada bitcoinden altın ve emtia endeksine doğru ve doğal gazdan bitcoine doğru tek yönlü volatilite yayılımı görülmüştür. Bitcoin ile emtilar arasında düşük düzeyde zamanla değişen volatilite yayılımı belirlenmiştir. Sonuçlar portföy yönetimi, portföy riskinin yönetilmesi, yatırım kararları açısından önem taşımaktadır.

A critical issue of diversification in portfolio management is the intra and inter-sectoral spread of risk. The aim of this study is to capture potential intra and inter sectoral risk spread. In this regard, the Bayesian Neural Networks (BNN) model was involved, the method being applied for a portfolio of 12 shares from the American index S&P 500, on the period January 1st, 2011 – January 28th, 2023. The expected shortfall was involved as a risk estimation measure and the Tabu Search learning algorithm of BNN was employed. The robustness of the results was tested at three significance thresholds namely, 0.85, 0.90 and 0.95. The differences of the results were highlighted on two subsamples, from January 1st, 2011 – December 31st, 2019, and January 1st, 2020 – January 28th, 2023. Evidence of intra and inter sectoral contagion was found on the full sample period, however during the financial turmoil period represented by the last sub-sample, the results display that the linkages between different sectors weakened to certain extents. The key contribution stands in the significant implications for portfolio risk management. The results highlight and strengthen the importance of building a portfolio based on an accurate selection of assets that are not inter-linked.

Risk management and dynamic portfolio selection with stable Paretian distributions

Our poster presents a research in progress conducted together with a FTSE 100 company aiming at reaching a higher level of maturity of their ITPPM process. This process was redesigned according to best practices and analyzed using the CommonKADS methodology. This work uncovered important shortcomings in the knowledge related to project and portfolio risk management. To enable appropriate understanding and management of risk at project and portfolio level, we designed a model for risk analysis which led us to specification, deployment (integration in the company's ITPPM portal) and evaluation of a risk Knowledge Base (KB).

The co-movement of revenue growth across different industries changes over the business cycle. Using a large sample of quarterly firm revenues, aggregated to industry data from 1969 to 2009, we demonstrate that the correlation is the highest during a crisis. Our findings of structural changes in correlation have implications for diversification decisions in portfolio analysis and risk management. The higher correlation in crisis periods increases the downside risk and bankruptcy probability of business portfolios. We test the hypothesis that average correlations are significantly different, by applying permutation and bootstrap techniques. As robustness checks, both correlations between industries and the aggregate market and correlations between earnings confirm our findings.

Qualified market risk management of asset and liability portfolios or trading activities is of key importance for banks and financial institutions. It is not only about quantitative measurement of the risks, but also about organizational and regulatory principles. Besides relatively simple market risk measures, we will define and explain various approaches to Value at Risk (VaR) and Conditional VaR estimation and backtesting. The two risk measures are used for day-to-day management as well as key regulatory capital concepts, or as tools of strategic risk management based on economic capital allocation. Market risk management, in particular in case of OTC derivatives, is also closely related to the counterparty credit risk management and measurement in terms of CVA (Credit Valuation Adjustment) that will be in detail discussed in the last section of this chapter.

Summary Probabilistic methods for reserves estimation, including uncertainty quantification and probabilistic aggregation, have gained widespread acceptance in the oil and gas industry, since the first comprehensive guidelines were issued by the Society of Petroleum Engineers (SPE) (Swinkels 2001). The probabilistic methods now used in the oil industry, as proposed in these guidelines, are similar to those also used in portfolio theory and risk management by the finance industry. A significant amount can be learned from the extensive experience with probabilistic methods and quantification of risk with measures like value-at-risk (VAR), in financial risk management. Especially, the guidelines issued by the Basel II Accord (Bank for International Settlements 2006) and the discussions since the 2008 financial crisis contain important lessons. In this paper, we examine a fundamental question: "Is the P90 reserves value an appropriate measure for quantifying the reserves’ downside?" For the P90 reserves value to be considered a good measure of the reserves’ downside, it needs to possess a number of basic characteristics involving P90 reserves for each field and the probabilistically aggregated P90 reserves for the portfolio of fields. Analogous to the definition of a coherent risk measure used in the finance industry, we define these characteristics for P90 reserves. The P90 reserves are as good a risk measure as VAR used in the financial industry. However, like VAR, it is not a coherent risk measure. A possible uncertainty scenario, in which one of these necessary characteristics does not hold, is given. An alternative measure of risk for quantifying the reserves’ downside, defined as the average reserves over the confidence interval higher than P90, is presented. This is a coherent risk measure. In this paper, we highlight the appropriateness and limitations of using the P90 reserves estimate as a measure of the reserves’ downside. Understanding of the limitations posed by using the P90 reserves value is vital in management of reserves risk.

Major segments of the U.S. economy are affected by weather. With the emergence of weather derivatives, exposure to weather‐related risk has evolved from being merely accepted. As a result, weather risk management strategies are increasingly being adopted in strategic decision‐making by senior management. Weather derivatives enable managers to focus on core operating risks by trading away those business exposures related to temperature, precipitation, snow level, etc. These contracts offer a unique opportunity to discretely trade a new category of risk, which was previously considered to be an inevitable cost of doing business. This article describes the weather derivatives market and its contracts and outlines the principles of pricing and risk analysis in weather markets. In closing, the article discusses the application of these products for portfolio and business risk management using illustrative examples from the energy markets.

As a data mining technique, independent component analysis (ICA) is used to separate mixed data signals into statistically independent sources. In this chapter, we apply ICA for modeling multivariate volatility of financial asset returns which is a useful tool in portfolio selection and risk management. In the finance literature, the generalized autoregressive conditional heteroscedasticity (GARCH) model and its variants such as EGARCH and GJR-GARCH models have become popular standard tools to model the volatility processes of financial time series. Although univariate GARCH models are successful in modeling volatilities of financial time series, the problem of modeling multivariate time series has always been challenging. Recently, Wu, Yu, & Li (2006) suggested using independent component analysis (ICA) to decompose multivariate time series into statistically independent time series components and then separately modeled the independent components by univariate GARCH models. In this chapter, we extend this class of ICA-GARCH models to allow more flexible univariate GARCH-type models. We also apply the proposed models to compute the value-at-risk (VaR) for risk management applications. Backtesting and out-of-sample tests suggest that the ICA-GARCH models have a clear cut advantage over some other approaches in value-at-risk estimation.

Fractal Market Hypothesis (FMH) was originated in 1960s and formulated in 1990s. As one of the forward theories in mathematical finance, FMH has offered a new prospect and methodology for the nonlinear dynamical capital market. This paper tentatively analyzes the cross-development between EMH and FMH, as well as the application and tendency of FMH. We firstly clarificate that FMH is not a substitution or alternative but a complement to EMH, and reveal that the intrinsic unity is their essential relationship. Then we emphasize repeatedly that studies of domestic mostly remain at initial stage. There have been too many empirical analyses to demonstrate the fractal structure of market, but relatively too little work of what the microscopic causes are or how to conduct portfolio selection and risk management according to FMH. Our basic discussion is supposed to conclude the logicality between different theories and application prospects of FMH. We hope cautiously that our personal views could inspire some guidance for further research.

A method is presented to estimate and decompose a portfolio's risk along independent factors. This decomposition is based upon a market's underlying independent risk factors, which are found empirically by using an inductive causal search algorithm that is based on independent component analysis. Since independent risk factors can be understood to always add risk to a portfolio, a portfolio manager can use them to better understand and budget risk. In contrast, portfolio management using the classic marginal analysis is confusing because adding a risky security to a portfolio might actually reduce the portfolio's risk. In a small application using the six most widely traded currencies (the Australian dollar, Canadian dollar, euro, sterling, Japanese yen and US dollar), independent-factor risk contributions are constrained during portfolio optimizations, and the internal risk characteristics of the resulting portfolios are found to compare favorably with those created by using constraints on the risk contributions of the original assets.