Portfolio Risk Research Articles

Sustainability risk in insurance companies: A machine learning analysis

AbstractSustainable development constitutes a global challenge today, and the sustainable development goals (Agenda 2030) will probably set the course for the coming decades. This paper discusses sustainability in insurance companies by combining two aspects: a social approach (the environmental impact) and a business approach (the prediction of claims due to climate change). Our objective is to analyse the impact of physical risk in a home insurance portfolio and to measure in economic terms the effect of climate change in the future, by applying machine learning methodologies. Two data sources are used: a Spanish insurance portfolio with 31,998 policies and claims from 2017 to 2022, and daily meteorological variables from 290 Spanish weather stations from 2000 to 2022. Two climate scenarios are considered: RCP 4.5 (medium impact) and RCP 8.5 (high impact). On average for the period 2023–2052, the results reveal that claims will increase by 105% for the 4.5 scenario and by 129% for the 8.5 scenario. Our paper makes a clear contribution to sustainability by analysing climate risks and their impact on an insurance portfolio. It shows the grave consequences of climate change for the insurance sector's solvency and the political implications for the financial system in general.

COVID-19 and redemptions from Irish-resident bond funds

This paper examines net redemptions from bond funds domiciled in Ireland at the onset of the COVID-19 pandemic. We analyse various empirical specifications to determine whether factors such as fund leverage, measures of liquidity, portfolio risk and portfolio concentration, among others, explain outflows from Irish-domiciled bond funds in March 2020. The findings indicate that funds with a larger share of short-term securities and riskier bond portfolios experienced higher redemptions. Our analysis also suggests that fund size and age are significant factors affecting outflows. When examining various sub-samples, we find evidence of more reactive behaviour among investors in actively managed funds compared to passively managed funds. We also find that retail bond funds demonstrate greater sensitivity to risk and leverage, while professional funds show evidence of lower risk aversion. These results provide insights that can help inform policymakers’ view of regulatory tools for market-based finance, a key priority internationally.

Monetary policy transmission under pandemic uncertainty: Effect on banks' risk and capital adjustments

AbstractThis paper investigates the effects of monetary policy on the simultaneous adjustments in asset portfolio risk and capital of banks amidst the uncertainty of the COVID‐19 pandemic, focusing on the 12 largest economies from 2018 Q1 to 2021 Q4. Results indicate that banks show lower portfolio risk and capital levels when the monetary policy stance is eased. However, amid heightened pandemic uncertainty, the risk‐reducing effect of monetary policy on banks amplifies, while bank capital levels remain unchanged. Heterogeneity analyses reveal that banks with higher levels of diversification and herding are more responsive to interest rates amid pandemic uncertainty, exhibiting lower risk exposure in their asset portfolios. Banks in countries adopting negative interest rate policies also tend to assume greater asset risk to accommodate the intended stimulus of monetary policies.

Dynamic portfolio optimization with the MARCOS approach under uncertainty

This paper introduces a dynamic portfolio selection approach that integrates the robustness of interval type-2 fuzzy sets (IT2FSs) with the flexibility of the MARCOS (Measurement of Alternatives and Ranking according to COmpromise Solution) method, offering a novel framework for asset evaluation amidst uncertainty. The IT2FSs enhance the adaptability of asset criteria representation, while the innovative application of MARCOS within the IT2FS environment refines the asset selection process. The weighted semi-absolute deviation metric is embraced to capture portfolio risk characteristic, which ingeniously harnesses the utility function values derived from the IT2F-MARCOS framework to delineate the anticipated return profile. On this basis, a dynamic bi-objective portfolio allocation model with realistic constraints and dynamic risk preference is formulated to rebalance portfolio periodically. Empirical evidence demonstrates the robustness and effectiveness of this approach compared to benchmark indexes, different allocation strategies, and the TOPSIS-based selection method, offering significant advancements in portfolio optimization for investors navigating uncertain markets. This study endeavors to contribute to the field of portfolio management, providing a thoughtful approach that enhances both theoretical understanding and practical application.

Applications of derivatives for portfolio risk management

Applications of derivatives for portfolio risk management

Quantitative Portfolio Management: Review and Outlook

This survey aims to provide insightful and objective perspectives on the research history of quantitative portfolio management strategies with suggestions for the future of research. The relevant literature can be clustered into four broad themes: portfolio optimization, risk-parity, style integration, and machine learning. Portfolio optimization attempts to find the optimal trade-off of future returns per unit of risk. Risk-parity attempts to match the exposure of various asset classes such that no single asset class dominates portfolio risk. Style integration combines risk factors on a security level such that rebalancing differences cancel out. Finally, machine learning utilizes large arrays of tunable parameters to predict future asset behavior and solve non-convex optimization problems. We conclude that machine learning will likely be the focus of future research.

Potential application of generative artificial intelligence and machine learning algorithm in oil and gas sector: Benefits and future prospects

With the rapid advancement of technology and societies, the global energy sector now acknowledges that by integrating contemporary digital technologies into their operations and capabilities, can improve their competitive advantage and innovation performance and processes. Moreover, energy operators are also facing a significant undertaking: how to best use and secure large amounts of data that promote sustainable productivity performance and minimise potential threats in the oil and gas value chain and project operations. In view of the foregoing, various facets like Generative Artificial Intelligence (GAI) and Machine Learning Algorithms (MLA) are increasingly gaining popularity within oil and gas sector operations. Thus, we explored how GAI and ML algorithms can enhance oil and gas value chain productivity performance. The Principal Component Analysis (PCA) was employed to identify significant GAI and MLA variables influencing performance in the oil and gas value chain, while Structural Equation Modelling (SEM) was used to test regression equations related to their application. The study found that risk portfolios and profiles can be appraised throughout the value chain by effectively utilising GAI and ML algorithms in upstream, midstream and downstream undertakings. While these findings are noteworthy and have significant implications for current practice, the paper advocates that an array of digital technologies beyond GAI and ML can still be examined during future studies to demonstrate a holistic perspective on how digital transformation can be achieved across the energy sector value and project operations.

Explainable machine learning for financial risk management: two practical use cases

We explore the potential of machine learning (ML) models applied in two financial risk management areas, i.e., credit risk management and financial risk hedging, through two practical use cases. This comparative study starts with the issue of explainability in complex ML models used in peer-to-peer lending for credit risk management. The first use case examines the limitations of using Kernel-SHAP with dependent features and evaluates different methods for estimating these dependencies using the Lending Club dataset. Our results suggest that accounting for feature dependence improves the understanding and robustness of prediction explanations. The second use case investigates a dynamic method for hedging foreign exchange risk in international equity portfolios, emphasizing the importance of accurate forecasts of currency returns. The analysis demonstrates that predictions yielded by ML models can significantly enhance the hedging of portfolios against currency risk. These findings highlight the transformative potential of advanced ML models in financial risk management, showcasing their capability to improve financial risk measurement and management. Further, our study outlines future research directions to advance this field.

The Role of Sex in the Assessment of Return and Downside Risk in Decumulation Financial Planning

This paper aims to assess the return and downside risk of a decumulation portfolio established at the retirement age of a senior, with a determined lifetime horizon differentiated by the sex of the citizen. To measure the portfolio’s return and downside risk, two ratios conditioned by seniors’ risk attitude towards portfolio failure are employed: the downside Sortino ratio and the downside risk–return ratio. Unlike other research in the field, this manuscript provides three portfolio compositions catering to different senior investment profiles: aggressive, moderate, and conservative. Additionally, it offers a decumulation horizon conditioned by the sex-specific life expectancy of the individual, instead of offering different scenarios for conducting a sensitivity analysis. Lastly, this study was conducted across three socioeconomically distinct countries: the US, Spain, and Japan. The results clearly demonstrate that both sex and nationality significantly influence the selection of the optimal decumulation portfolio composition aimed at exhausting funds by the senior’s demise.

Analisis Markowitz dan Model Indeks Tunggal dalam Pembentukan Portofolio Optimal Saham Jakarta Islamic Index Periode 2019-2023

This research is motivated by the increasing number of sharia investors each year and the uncertainty of stock prices incorporated in the Jakarta Islamic Index in 2019-2023 so there is a needed to plan optimal portfolio to reduce the risk. Sampling in this study using purposive sampling method that meets the sample criteria as many as 15 stocks. The analysis technique used is descriptive analysis and hypothesis testing is done using the Independent Sample T-Test. The results showed that there were 3 stocks incorporated into the optimal portfolio of the Markowitz model, namely ADRO, ANTM, and BRPT, with an expected portfolio return of 0.0238 and a portfolio risk of 0.1066. And there are 4 stocks that are incorporated into the optimal portfolio of the Single Index Model, namely ADRO, BRPT, ANTM, and INCO, with an expected return of 0.0215 and a portfolio risk of 0.1035. Therefore, Markowitz portfolio is better to use than the Single Index Model portfolio because it has a greater expected return than the Single Index Model. However, statistical testing using t-test shows that the expected return and risk of the optimal portfolio of the Markowitz Model and the Single Index Model are not significantly different.

A new portfolio approach integrating three-way decision and Encoder–Decoder network

In the stock market, it can be challenging to predict stock trends and identify stocks with investment potential due to uncertainty and risk. Accurate predictive models and reliable asset preselection methods are essential for portfolio management. This paper proposes an integration of the deep learning model, the three-way decision (3WD) theory, and the Mean-Variance (MV) method for asset preselection and optimal asset allocation. In the initial stage, an attention-based Encoder–Decoder model is used to predict asset returns and calculate volatility. It outperforms other benchmark models regarding relative error, absolute error, and directional accuracy. The subsequent stage involves selecting stocks based on expected returns and volatility characteristics. The 3WD theory is then used to identify the delayed decision set for implementing additional investment strategies to hedge portfolio risk and enhance returns. Finally, the MV model is employed for investment portfolio optimization. The proposed model is validated using a substantial dataset from the A-share market’s SSE 50 Index from January 2010 to December 2022. Results indicate that the proposed model outperforms benchmark models in terms of daily average returns, annualized Information ratio, Sortino ratio, and other aspects under certain trading costs. However, further exploration is required to establish a mechanism that limits the quantity of preselected assets to ensure its broad applicability.

Survey-based measures of risk attitudes and portfolio risk: Evidence from pension participants

We use a unique dataset of pension participants in Turkey to evaluate the effectiveness of a risk questionnaire developed by the regulatory authority. Our analysis includes a reliability assessment (Cronbach’s α=0.73) and a factor analysis that reveals two latent constructs: risk attitude and financial situation/literacy. Although both factors show a significant positive relationship with participants’ portfolio risk, the overall explanatory power remains low, with an R2 of 0.134. Comparing these factors in terms of their contribution to predictive validity, we demonstrate that the risk attitude factor—formed from questions directly addressing financial risk-taking—exhibits significantly greater predictive power than the financial situation/literacy factor, which pertains to questions about the financial situation and self-assessed financial literacy. Our results imply that demographic factors like gender, education level, marital status, and age show weak predictive power for portfolio risk, suggesting that observed behavior in risky choices is more influenced by domain-specific attitudes.

Evaluation of counterparty credit risk under netting agreements

We investigate counterparty credit risk and credit valuation adjustments in portfolios including derivatives with early-exercise opportunities, under a netting agreement. We show that credit risk and netting agreements have a significant impact on the way portfolios are managed (that is, on options’ exercise strategies) and, therefore, on the value of the portfolio and on the price of counterparty risk. We derive the value of a netted portfolio as the solution of a zero-sum, finite horizon, discrete-time stochastic game. We show that this dynamic-game interpretation can be used to determine the value of the reglementary capital charges required of financial institutions to cover for counterparty credit risk and we propose a numerical valuation method. Numerical investigations show that currently used numerical approaches can grossly misestimate the value of credit valuation adjustments.

Diversifying crude oil price risk with crude oil volatility index: The role of volatility-of-volatility

To understand the diversification benefit of crude oil volatility, we examine the return-volatility relation in the crude oil market, given the interaction of the volatility (VOL) and the volatility-of-volatility (VOV). We develop a novel empirical model of the crude oil price and crude oil volatility index (OVX) returns incorporating both time-varying and state-dependent variances and correlations, thus allowing us to identify distinct market regimes of VOL and VOV. We find that the behavior of the return-volatility relation is contingent on the prevailing VOV regimes. Specifically, in a low (high) VOV regime, the relation becomes less (more) negative as VOL increases. These empirical results therefore imply that the diversification benefit of crude oil volatility is far from uniform across the different market states. Finally, using our proposed empirical model, we demonstrate the economic significance of recognizing both the time-varying and state-dependent variances/correlations in portfolio risk forecasting and construction.

A combined framework to explore cryptocurrency volatility and dependence using multivariate GARCH and Copula modeling

During the last years, cryptocurrencies have been increasingly becoming a relevant subject of academic researchers and investors. This paper adopts a novel framework that combines a multivariate Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) and Copula modeling in a two-stage approach to analyze the cryptocurrency volatility dynamics. By combining the aforementioned techniques, on top of showing that price movements in one cryptocurrency can significantly influence others, the use of copulas highlight how these effects can vary across different parts of distributions and thus for different types of events with respect to their extreme nature. The interconnectedness complexity should be taken into consideration when managing risk in portfolio and constructing relevant models.

Towards a comprehensive framework for risk assessment of organizational development project portfolios

The benefits of risk management in the context of project portfolios have been widely recognized in the literature. However, approaches that assess the risk of organizational development project portfolios from the perspective of how the portfolio delivers value to the parent organization remain largely unexplored. To address this gap, our research takes a constructivist approach and an organizational perspective on project portfolios. We conducted twenty-eight semi-structured interviews and used thematic analysis to identify and relate four themes of a comprehensive project portfolio risk assessment (PPRA) framework: "project portfolio as the organizational unit for PPRA"; "organizational capabilities as portfolio outcomes in which PPR can be assessed"; "project portfolio levels as sources of risk factors in PPRA"; and "balance between project portfolio attributes complexity". Within the framework of organizational development project portfolios, this study contributes to our understanding of PPRA by providing two propositions: (1) The capabilities to be generated by the project portfolio can be used as the portfolio primary results on which PPRA can assess the risk of the project portfolio, establishing the impact of PPR on the project portfolio value delivering to the parent organization, and (2) The risk factors that impact the project portfolio expected results can be represented into PPRA as ‘output-related’ risk factors and ‘outcome-related’ risk factors.

Exploring interconnections and risk evaluation of green equities and bonds: fresh perspectives from TVP-VAR model and wavelet-based VaR analysis

PurposeThis study attempts to examine the time-varying volatility spillovers between environmentally sustainable assets and quantify the value-at-risk of the portfolios across various frequencies.Design/methodology/approachTo accomplish these objectives, this paper utilizes a connectedness index-based TVP-VAR model and applies the wavelet-based VaR ratio to daily data spanning from January 2018 to September 2023.FindingsThe empirical findings reveal a notable increase in the connectedness index between green stocks and green bonds during the COVID-19 crisis, signifying evidence of a contagion effect. The portfolio’s risk ratio also exhibited a sharp rise amid the pandemic, particularly over medium and long-term horizons, driven by increased spillover among green assets. Notably, our analysis indicates that green bonds influence the connectedness system between green stocks and the value-at-risk ratio, reducing volatility spillover and portfolio risk ratios across various investment horizons. These results highlight the role of green bonds as an effective diversification asset against the risks associated with green equities.Originality/valueThis research investigates the dynamic connectedness and value-at-risk ratio between eight green sectoral renewable energy and non-energy equities and green bonds. We put forward some portfolio implications for green investors with an environmental consciousness who desire to decarbonize their portfolios and mitigate environmental issues.

A Study on the Risks of Real Estate Investment

This paper examines the risks associated with real estate investment, leveraging Modern Portfolio Theory (MPT) introduced by Harry Markowitz and later applied to real estate by Nigel Dubben and Sarah Sayce. MPT emphasizes balancing expected returns and risk through diversification, crucial in real estate due to its low correlation with other assets and its inflation-hedging properties. Despite global economic integration increasing systemic risks, real estate remains a key asset class for risk management. The literature review highlights traditional strategies focusing on diversifying by property type and geographic location. Studies show mixed results: some suggest property type diversification yields higher returns, while others find geographic diversification more effective for risk mitigation. Chinese market studies reveal that real estate investments can provide predictable returns and act as a hedge during economic downturns. Research on Beijing and Shanghai supports the effectiveness of geographic diversification within China. Applying MPT to real estate, the paper demonstrates through case studies how investment combinations can balance risk and returns. It discusses the Efficient Frontier, CAPM, and Arbitrage Pricing Theory to illustrate the relationship between risk and return in real estate portfolios. The analysis concludes that diversification strategies, though complex, are essential for optimizing performance and mitigating risks in real estate investments.

Ethical consumerism, supply chains, and deceptions with RFID-based systems

Ethical consumerism has led manufacturers and retailers to develop new initiatives to align their products and services with related requirements, such as the management of supply chains for ethically produced products. To this end, recent years have witnessed the growing reliance on technological innovations to corroborate claims on ethically produced products. RFID (Radio-Frequency Identification)-based systems have found a natural fit for such applications due to their ability to uniquely identify individual items and locally store their characteristics and history. While the benefits of such a setup are clear, there is a paucity of research on associated unethical risks. What is often unclear is the possibility of deception when RFID-generated information is used to certify ethical production. We draw on stockholder theory, stakeholder theory, social contract theory, and Mason’s information ethics theory to study the underlying dynamics. We show that enhancing RFID information accessibility and accuracy in supply chains is key to mitigating the unethical risk of deception and ensuring that RFID-based systems can truly certify ethically produced products. We develop a portfolio of such risks, identify means to mitigate identified risks, and then use a case study to examine the impact of varying degrees of RFID-generated information accessibility and accuracy on the detection and prevention of associated deceptions.

ANALYSIS OF OPTIMAL PORTFOLIO FORMATION ON IDX30 INDEXED STOCK WITH THE MEAN ABSOLUTE DEVIATION METHOD

In investing in stocks, an investor must be able to form a stock portfolio to obtain optimal results. Factor analysis is one way to select stocks to form a portfolio. Factor analysis with Principal Component Analysis (PCA) extraction is used to summarize many variables into new smaller factors by producing the same information. The new factor formed is called a portfolio. This study aims to form an optimal portfolio using the Mean Absolute Deviation (MAD) method, which is an alternative to Markowitz optimization, and assess the stock portfolio's performance using the Sharpe index. This research uses IDX30-indexed stocks because the stocks in this index have high market capitalization and liquidity. The data used in this study are daily close stock price data on the IDX30 index from September 20, 2022, to September 20, 2023. The data used is secondary data obtained from the official website https://finance.yahoo.com/. From the analysis, three stock portfolios were obtained. With MAD optimization, the investment weight of each stock is obtained namely, in the first portfolio, the investment weight of AMRT shares is 21.95%, BBCA shares are 30%, BBNI shares are 18.05%, and BBRI shares are 30%. In the second portfolio, the investment weight of AKRA shares is 34.03%, BRPT shares are 40%, and MEDC shares are 25.97%. In the third portfolio, the investment weight of BMRI shares is 50%, and INDF shares are 50%. By measuring the performance of the Sharpe index, the optimal portfolio is obtained in the second portfolio with an expected return portfolio of 0.155% and a portfolio risk of 1.927%.