Risk Measures Research Articles

Robust portfolio management: A novel multi-task learning model fusing predicted returns and residual data under the framework of Mean-VaR

We investigate how to build a robust portfolio by introducing a novel multi-task learning model that fuses predicted returns and residual data to assess the portfolio risk under the decision-making framework of Mean-VaR. A common way to build a portfolio is to predict the return of assets and then allocate weights according to the predicted return and corresponding risk. However, predicting asset returns accurately in financial markets remains a challenge. To improve prediction accuracy and, more importantly, effectively reduce risk in the portfolio, we adopt the multi-task learning anomaly detection (MTLAD). In this model, predicting asset returns using deep learning model (long short-term memory, LSTM) is the main task, and anomaly detection is the auxiliary task. We then combine the predicted returns and residual data to evaluate the risk measure when allocating the asset weights. Furthermore, we perform an extensive numerical investigation based on data in the Chinese financial market. Results obtained show that our robust portfolio management approach has great potential compared with multiple benchmarks.

A stochastic optimisation model to support cybersecurity within the UK national health service

Over the past decade, the adoption of new digital technologies in healthcare has surged, significantly enhancing care delivery and accessibility. However, this digital transformation has been accompanied by a sharp increase in cyber-attacks, posing severe risks to hospital functionality and patient safety. To address the challenge of planning for uncertain future cyber incidents, we propose a two-stage stochastic model designed to bolster the cyber resilience of healthcare providers by selecting optimal countermeasures in preparation for upcoming cyber incidents. Numerical tests demonstrate the model’s effectiveness, with the Value of the Stochastic Solution showing a 21% improvement over a deterministic approach. To be optimally equipped even for low-probability high-impact attacks we incorporate the risk measure Conditional Value-at-Risk. The corresponding countermeasure solution led to 44% fewer rejected patients in a worst-case scenario. The robustness of the proposed solution is underscored by its consistent performance across various scenarios, budget levels, and risk preferences, making it a reliable tool for enhancing cybersecurity in healthcare. These results highlight the importance of tailored, robust cybersecurity strategies in healthcare, ensuring preparedness for a wide range of potential threats.

Warren Buffett and Berkshire Hathaway's Recent Investment Strategy Changes and the Reasons for the Corresponding Risk Measures

With the development and changes of the world economy, the size of the global securities market is gradually increasing, and the investment methods available for citizens to choose from are becoming more diverse. Stocks, as one of the most important investment methods, have also received increasing attention from investors. After experiencing a slow economic recovery, the distribution of global stock and securities markets is also constantly expanding. In recent years, the global ETF market has crossed new milestones, with a scale exceeding $11 trillion for the first time, showing an unstoppable development trend, reflecting the recovery and growth of the global securities market after experiencing the financial crisis. In addition, global stock indices have generally risen. Especially for assets that are lagging behind in 2023, it shows an upward trend in the global securities market after entering 2024. Due to the continuous changes and maturity of the economic landscape and securities market, it has brought huge social dividends and increased investor willingness. As an outstanding representative in the fields of stock and securities investment, Buffett's investment ideas and strategies have been highly valued by the general public. Therefore, studying typical cases of Buffett's investments has a guiding significance. This article will analyze Buffett's investment preferences and performance from 2023 to the first half of 2024, starting from the current international background and combining Buffett's value investment philosophy. It will provide reference suggestions for investment industry practitioners and regulatory agencies.

Social vulnerability is associated with advanced breast cancer presentation and all-cause mortality: a retrospective cohort study

BackgroundDisparities in breast cancer mortality persist despite improvements in screening and therapeutic options. Understanding the impact of social determinants of health on disparate breast cancer outcomes is challenging due to heterogeneity of prior assessments. We examined the association between social vulnerability and breast cancer stage at diagnosis and mortality using a standardized measure of population risk for external stressors on health.MethodsUsing institutional cancer registry data, female patients aged 18 or older diagnosed with breast cancer between 2012 and 2019 were assigned a 2018 Social Vulnerability Index (SVI) rank based upon home address census tract. We used multinomial logistic regression and Cox proportional hazards model to examine the relationships between SVI and breast cancer stage at diagnosis and all-cause mortality. Covariates included age and, when assessing mortality, cancer stage, comorbidities, body mass index, insurance type, and treatment regimen.ResultsA total of 3,499 women with a median age of 59 (IQR 48–69) were included. 60% were White and 31% were Black. Median SVI was 0.36 (IQR 0.14–0.68) and median follow-up was 58 months (IQR 37.3–83.9). On adjusted analyses, each decile increase in SVI resulted in an 11% (OR 1.11, 95% CI 1.06–1.16, p < .001) and 15% (OR 1.15, 95% CI 1.09–1.21, p < .001) greater odds of presenting with Stage III or IV breast cancer, respectively, compared to DCIS. For patients who underwent surgery (N = 2916), each decile increase in SVI was associated with a 6% increase in all-cause mortality risk (HR 1.06, 95% CI 1.01–1.12, p = .01). Mortality risk was 1.5 times (HR 1.52, 95% CI 1.02–2.26, p = .04) greater for those in the most vulnerable quartile compared to the least vulnerable quartile.ConclusionsWomen living in socially vulnerable communities presented with more advanced breast cancers and suffered worse survival. The SVI can be used to identify patients at risk for delayed cancer presentation and increased mortality. This tool can inform geographically targeted resource allocation and interventions aimed at reducing breast cancer care disparities.

Longitudinal analysis of lifestyle risk factors, nutrition status, and drivers of food choice among urban migrants in Ulaanbaatar, Mongolia and Almaty, Kazakhstan: a formative study.

To quantify and compare concurrent within-person trends in lifestyle risks, nutrition status, and drivers of food choice among urban migrants in Central Asia. We collected panel data on household structure, drivers of food choice, nutrition knowledge, and diverse measures of nutrition status and lifestyle risk from urban migrants at 0, 3, 6, and 9 months using harmonized methodology in two cities. Trends were analyzed using mixed-effects models and qualitatively compared within and between cities. Ulaanbaatar, Mongolia and Almaty, Kazakhstan. 200 adults (22-55 years) who migrated to these cities within the past 2 years. Adjusting for age and sex, each month since migration was positively associated with fasting triglycerides in Almaty (0.55 mg/dL; 95%CI: 0.13-0.94) and BMI (0.04 kg/m2; 95%CI: 0.01-0.07), body-fat (0.14%; 95%CI: 0.01-0.26), and fasting glucose (0.04 mmol/L; 95%CI: 0.02-0.05) and lipids in Ulaanbaatar (p<0.05). In Almaty, nutrition knowledge (measured using an objective 20-point scale) declined despite improvements in diet quality (measured by Prime Diet Quality Score). Influence of food availability, price, and taste on food choice increased in Almaty (p<0.05). Upon multivariable-adjustment, nutrition knowledge was positively associated with diet quality in Almaty and adherence to "Acculturated" diet patterns in both cities (p<0.05). Different trends in smoking, sleep quality, and generalized anxiety were observed between cities. Findings indicate heterogenous shifts in nutrition, lifestyles, and drivers of food choice among urban migrants in Central Asia and provide an evidence base for focused research and advocacy to promote healthy diets and enable nutrition-sensitive food environments.

Market Risk Measures Impact on Systemic Risk in Indonesia Banking Industry

This study investigates the relationship between market risk measures and systemic risk in Indonesia's banking sector. It aims to inform policymakers and regulators in promoting financial stability. By examining how market risk measures, specifically total risk encompassing systematic and idiosyncratic components, influence systemic risk in Indonesia's banking system, this study addresses a notable research gap, particularly in emerging markets like Indonesia. This research contributes to the understanding of systemic risk dynamics in an emerging market context, offering insights into how market risk measures contribute to systemic risk. Employing a quantitative approach, this study utilizes secondary data from the Indonesia Stock Exchange and Datastream Refinitiv Eikon. Non-probability sampling selects banks listed on the Indonesia Stock Exchange, with daily stock price data used to construct market risk measures. Systemic risk is measured using both CoVaR and MES, and regression analysis is employed to explore the relationship between market risk and systemic risk. The study reveals a significant positive association between total risk and systemic risk, highlighting the crucial role of idiosyncratic risk in this relationship. These findings underscore the importance of considering both systematic and idiosyncratic market risk when assessing systemic risk in Indonesia's banking sector. The study emphasizes the need for robust risk management practices and regulatory measures to ensure financial stability in emerging markets.

Introducing conditional expected loss: A novel metric for risk investment analysis

Risk analysis is crucial in real asset investment projects. However, existing risk measures like VaR (value at risk) and CVaR (conditional value at risk) may not fully capture potential losses in such scenarios. Consequently, the current literature lacks an indicator that accurately estimates the expected value in the event of financial insufficiency. To fill this gap, this article introduces the conditional expected loss (CEL) metric, a novel approach that estimates the average loss expected in the event of financial deficits within an investment project and provides extensive numerical modeling and a detailed real-world example. This novel metric enhances risk analysis and decision making, particularly evaluating financial insufficiency within projects with limited managerial flexibility and a higher likelihood of financial deficits. By incorporating CEL alongside other risk and return metrics, practitioners gain a more comprehensive understanding of project risks, ultimately leading to better investment choices.

Risk and return spillovers among developed and emerging market currencies

We develop a network model capturing the dynamic interactions among foreign exchange (FX) returns and realized risk measures for 20 developed market (DM) and emerging market (EM) currencies. We show that DM currencies are more integrated within the network than EM currencies on average and tend to become more dependent on external conditions over time. Spillovers between DMs and EMs evolve more rapidly than spillovers within DMs and within EMs and are a major contributor to overall spillover dynamics. Auxiliary regressions reveal that the net DM-to-EM spillover comoves with global factors known to drive EM capital flows.

Assessing the role of ESG evaluation in market risk management for sovereign bond investments

ABSTRACT With the growing emphasis on responsible investing, the role of environmental, social, and governance (ESG) factors in risk management has become significant, extending to the field of sovereign bonds. This study examines the role of ESG evaluations in the risk management of sovereign bond investments. Across fifty countries, including developed and emerging countries, our findings indicate that, even after controlling each country's yield levels and fiscal conditions, nations with lower ESG scores tend to face higher market risks, notably regarding tail risk measures. This pattern is especially pronounced in the bonds of emerging countries. The research highlights that ESG evaluation of sovereign bonds can provide insight into the likelihood of unforeseen events, such as political turmoil and natural disasters, often not reflected in sovereign bond yields.

Randomized controlled trial of a pilot PrEP linkage intervention for individuals leaving incarceration in a southern state: Design and baseline characteristics.

We report baseline characteristics of a pilot intervention, PrEP-Link, which uses a community health worker (CHW) model to provide navigation to PrEP, the daily HIV preventative medication, and other medical and social services upon release from incarceration. This pilot study uses a randomized controlled trial design. The control group receives enhanced standard of care, and the intervention receives enhanced standard of care plus personalized navigation services from the CHW for up to one year. PrEP-Link is modeled after the Transitions Clinic Program, where a CHW who has lived experience of incarceration builds close relationships with individuals and community partners. After COVID-19 restrictions prevented recruitment within local jails, recruitment for this study took place in local reentry centers which house individuals as they near completion of their jail or prison sentence. Data are collected at baseline, 6 months, and 12 months. Planning and reporting was guided by the CONSORT 2010 checklist. We enrolled 80 participants between September 2021 and April 2023. Thirty-nine participants were assigned to the control group and forty-one to the intervention group. Data collected at baseline included measures of PrEP usage, HIV risk, drug and alcohol use, healthcare usage, and history of incarceration. Analysis of baseline characteristics show comparability of both demographic and HIV-related risk factors between the two arms. At baseline, participants had high clinical indication for potential PrEP benefit, particularly with respect to self-reported intravenous drug use and condomless sex. Participants responded with high PrEP acceptability within both study arms. Participants reported low preventative healthcare utilization at baseline. Barriers to accessing PrEP among the study population are significant. Results of this pilot RTC will help inform CHW lead PrEP-linkage interventions for people leaving incarceration.

Inferring stability and persistence in the vaginal microbiome: A stochastic model of ecological dynamics.

The interplay of stochastic and ecological processes that govern the establishment and persistence of host-associated microbial communities is not well understood. Here we illustrate the conceptual and practical advantages of fitting stochastic population dynamics models to multi-species bacterial time series data. We show how the stability properties, fluctuation regimes and persistence probabilities of human vaginal microbial communities can be better understood by explicitly accommodating three sources of variability in ecological stochastic models of multi-species abundances: 1) stochastic biotic and abiotic forces, 2) ecological feedback and 3) sampling error. Rooting our modeling tool in stochastic population dynamics modeling theory was key to apply standardized measures of a community's reaction to environmental variation that ultimately depends on the nature and intensity of the intra-specific and inter-specific interaction strengths. Using estimates of model parameters, we developed a Risk Prediction Monitoring (RPM) tool that estimates temporal changes in persistence probabilities for any bacterial group of interest. This method mirrors approaches that are often used in modern conservation biology in which a measure of extinction risks is periodically updated with any change in a population or community. Additionally, we show how to use estimates of interaction strengths and persistence probabilities to formulate hypotheses regarding the molecular mechanisms and genetic composition that underpin different types of interactions. Instead of seeking a definition of "dysbiosis" we propose to translate concepts of theoretical ecology and conservation biology methods into practical approaches for the management of human-associated bacterial communities.

Time-varying stock return correlation, news shocks, and business cycles

The cross-sectional average of the pairwise correlations between U.S. stock returns is considered as a measure of risk to aggregate wealth priced by the stock market. We show that this measure predicts future U.S. output growth at a horizon of one to four years. A stronger average correlation of stock returns foreshadows significantly lower future output growth, even when controlling for some other widely used financial predictors. An innovation to average correlation gives rise to macroeconomic dynamics that resemble negative news about future total factor productivity (TFP) in a vector autoregression. TFP news shocks thus appear to be a key source of aggregate risk priced into stocks.

Moving toward Equity through Embedded ELSI Ethnography.

This paper describes the unique values of, challenges within, and opportunities presented by embedded ELSI ethnography. Drawing from our six-year embedded ELSI study of the WISDOM (Women Informed to Screen Depending on Measures of Risk) trial, we present three examples of the variable ways we engaged with the WISDOM trial's scientific team. WISDOM is a preference-sensitive, pragmatic, randomized controlled trial of risk-based breast cancer screening informed by genomics. Our embedded ELSI approach included multiple modes of engagement: (a) Trial investigators sought bioethics expertise; for example, we were asked to consult on traditional bioethics topics such as consent as well as more complex questions about whether to implement a specific risk-assessment approach on only one race-defined group of trial participants. (b) As the ELSI investigators, we identified ethical concerns in issues that surfaced via ethnography and considered them in the Bioethics Working Group; for example, there were concerns about the implementation processes that the WISDOM team viewed as logistical challenges. (c) Our presence in WISDOM working group conversations and our expertise on classic social science topics, including race and gender, offered opportunities to engage on the spot with topics such as how to include transgender participants in a trial initially focused on "women's health"; through such engagement, the value of social science became clear to the trial investigators. The paper elaborates on the dynamic relationship between our ethnographic observations, the Bioethics Working Group discussions, and the contributions of each to our real-time ELSI interventions in these examples. The methods and experiences we describe here suggest modes of engagement that, in combination, have the potential to expand the role of ELSI to offer real-time intervention on issues related to equity, inclusion, and justice in genetic and genomic research.

The influence of uncertainty on commodity futures returns and trading behaviour

We utilise measures of economic policy uncertainty (EPU) and geopolitical risk (GPR), as well as commitments of traders (COTs), to investigate the influence of uncertainty on commodity markets. We find that uncertainty has a significant influence on returns, but the direction of the response is due to whether uncertainty emanates from demand shocks (EPU) or supply shocks (GPR). Uncertainty is also positively related to volatility and trading volume. Importantly, we also find that net positions of both commercial and non-commercial traders are influenced by uncertainty levels. Examination of high uncertainty and recessionary periods indicates that our results are state dependent.

HLA EPLET Frequencies Are Similar in Six Population Groups and Are Expressed by the Most Common HLA Alleles.

The degree of immunological compatibility between donors and recipients greatly impacts allograft survival. In the United States kidney allocation system, HLA antigen-level matching has been shown to cause ethnic disparities and thus, has been de-emphasised. However, priority points are still awarded for antigen-level zero-ABDR matching, zero-DR matching and one-DR matching. Recently, the degree of HLA molecular (eplet) mismatch has emerged as a more accurate measure of immunological risk, and eplet mismatch load has gained attention as a possible biomarker to improve HLA compatibility. However, little is known about the frequency of eplets in population groups, which is a necessary step to ensure that candidates from any ethnical background can have similar chances at a well-matched organ. Eplet frequencies were estimated using HLA alleles in the Common, Intermediate and Well-Documented (CIWD) 3.0.0 catalogue for six population groups: African-American (AFA), Asian-Pacific Islander (API), European/European descent (EURO), Middle East/North Coast of Africa (MENA), Hispanic/Latino (HIS) and Native-American (NAM). We determined that 98.6% (484 out of 491) of HLA eplets are expressed by the common HLA alleles in all population groups. Of the seven eplets that were expressed by less common HLA alleles, six were Class I eplets and one was expressed by HLA-DQB1 alleles and most were expressed by HLA alleles that were more commonly observed in European/European descent populations. Our observations indicate that HLA eplets will not cause any significant disparity if applied to HLA molecular compatibility, regardless of the ethnic origin of both recipients and donors.

Health risk assessment using Monte-Carlo simulations due to arsenic contamination in groundwater in Punjab.

Groundwater contamination is a major environmental concern in many regions of India, including several districts of Punjab. In this study, a comparison is carried out between the deterministic and probabilistic approaches for calculating health hazard parameters due to arsenic contamination in groundwater in India. The probabilistic calculations are carried out through Monte-Carlo simulations to quantify the hazard index (HI) and carcinogenic risk. Sensitivity analysis is carried out to determine the contribution of input variables to the HI. From the deterministic and probabilistic approach, an HI greater than one is obtained in adults for all districts except Moga, whereas, for children, the HI is greater than 1 in all districts. This suggests a higher probability of risks, such as developmental problems and cardiovascular disorders. Excess lifetime carcinogenic risk, a measure of carcinogenic risk, is found above the US Environmental Protection Agency's recommended range of 1 × 10-6 to 1 × 10-4 in all districts. These values clearly indicate the long-term carcinogenic danger associated with arsenic exposure since they are far above the tolerable risk threshold of 1 × 10-4. Thus, necessary mitigation measures should be taken, and routine groundwater monitoring should be performed.

Risk management, the board and the C-suite: The adaptive art of communication in times of change

Financial institutions have always been tasked with mitigating risks due to their role in financial markets. Risk management is a fundamental component of financial intermediation, which since the late 1970s has become more structured, demanding more sophisticated tools and techniques and requiring Chief Risk Officers (CRO) to possess advanced technical skills, particularly in the hard sciences. Nevertheless, technical skills are not the sole expertise required nowadays; the participation of risk managers in strategic meetings calls for negotiation skills to interact with those responsible for drafting the business plan, typically the Chief Financial Officer (CFO), and communication skills to connect with board members who set the strategic direction. While negotiation can be mediated through the General Manager (GM) or the Chief Executive Officer (CEO), communication with the board is direct and immediate. Traditionally, effective communication is not generally regarded as a typical quality of financial risk managers, since this is a substantially different skill from the technical expertise needed. Regulators require that banks implement company-wide risk management frameworks with the use of analytical models for the measurement and control of quantifiable risks. In addition, corporate governance guidelines advocate for the ‘business partner’ role in risk management. The question is: how do risk officers balance their dual role as a ‘compliance champion’ and a ‘business partner’? Effective communication may provide a solution. This paper outlines the goals and tools for effective communication for risk management to enable sound decision making and thereby counteract the group thinking that may lead to poor decisions, often resulting in an imbalance between risk taking and control that can undermine the operational resilience of banks.

Cardiopulmonary coupling measures of sleep stability and risk of cognitive impairment in community‐based older men

Cardiopulmonary coupling measures of sleep stability and risk of cognitive impairment in community‐based older men

The Dynamic Impact of World Pandemic Uncertainty on Stock Market Crash Risk: An International Study

This paper examines the dynamic impact of world pandemic uncertainty on the crash risk of international stock markets. The results show world pandemic uncertainty has a positive impact on the crash risk. The effect is largest in the first quarter and significantly fades away in the following three quarters after the shock. Our results are robust for developed and emerging markets and for alternative measures of crash risk and world pandemic uncertainty.

Do PCAOB Inspections Change the Effect of Litigation Risk on Audit Quality?

Synopsis The research problem This study examines whether the effect of litigation risk on audit quality changes when auditors face high versus low regulatory risk under the Public Company Accounting Oversight Board (PCAOB) inspection regime. Motivation The establishment of the PCAOB under the Sarbanes–Oxley Act marked a fundamental change in the regulatory environment for the auditors. At the core of the PCAOB’s oversight of the audits of public companies are the inspections of individual audit engagements. While prior studies have found a positive effect of the PCAOB inspection program on audit quality, little is known about whether and how the regulatory risk imposed by PCAOB inspections influences the effect of litigation risk on audit quality. To the extent that both regulatory oversight and litigation threat share the common objective of motivating auditors to exert sufficient effort and perform high-quality audits, we are motivated to examine whether and how the stringent regulatory environment under the PCAOB regime affects auditors’ perception of, and response to, litigation risk. Hypothesis We posit that the significant and constant regulatory threat imposed by PCAOB inspections may change auditors’ perception of litigation, which is more remote and less frequent relative to regulatory inspections, such that litigation risk has a smaller effect on audit quality/effort when auditors face high versus low regulatory risk arising from the PCAOB inspections. However, there also exists opposing arguments that would suggest a nondecreasing effect of litigation risk on audit quality in the presence of high regulatory risk. Thus, we present our hypothesis in the null form: the effects of litigation risk on audit quality are not associated with regulatory risk under the PCAOB inspection regime. Target population Researchers, audit practitioners, regulatory authorities, policymakers, and firms. Adopted methodology We employ multivariate regression analysis featuring the ordinary least squares (OLS) estimation to test our hypothesis. In additional tests, we also use the probit estimation for binary dependent variables. Analyses Using a sample of 34,559 client-firm year observations for the period between 2005 and 2019, we estimate a multivariate regression model to examine whether and how the audit deficiencies identified in the PCAOB inspections influence the effect of litigation risk on audit quality exhibited at the client level. Findings Our main findings show that, while regulatory risk (proxied by PCAOB-identified audit deficiencies) and litigation risk (proxied by lawsuits filed against auditors/firms) each has a positive effect on audit quality, the interaction term of the two is negatively associated with audit quality. This rejects our null hypothesis and indicates that litigation risk has a smaller motivational effect when the auditors are faced with greater regulatory risk. Similar results are obtained using audit fees, financial restatements, and the propensity to report small profits as the alternative measures of audit quality. We further validate those results with alternative measures of regulatory risk and litigation risk. Our empirical evidence corroborates the views of audit practitioners, surveyed in Westermann et al. (2019), that auditors are increasingly concerned about regulatory risk, as opposed to litigation risk, under the PCAOB regime.