Search results

Machine learning (ML), and deep learning in particular, is gaining traction across a myriad of real-life applications. Portfolio management is no exception. This paper provides a systematic literature review of deep learning applications for portfolio management. The findings are likely to be valuable for industry practitioners and researchers alike, experimenting with novel portfolio management approaches and furthering investment management practice.

This review follows the guidance and methodology of Linnenluecke et al. (2020), Massaro et al. (2016) and Fisch and Block (2018) to first identify relevant literature based on an appropriately developed search phrase, filter the resultant set of publications and present descriptive and analytical findings of the research itself and its metadata.

The authors find a strong dominance of reinforcement learning algorithms applied to the field, given their through-time portfolio management capabilities. Other well-known deep learning models, such as convolutional neural network (CNN) and recurrent neural network (RNN) and its derivatives, have shown to be well-suited for time-series forecasting. Most recently, the number of papers published in the field has been increasing, potentially driven by computational advances, hardware accessibility and data availability. The review shows several promising applications and identifies future research opportunities, including better balance on the risk-reward spectrum, novel ways to reduce data dimensionality and pre-process the inputs, stronger focus on direct weights generation, novel deep learning architectures and consistent data choices.

Several systematic reviews have been conducted with a broader focus of ML applications in finance. However, to the best of the authors’ knowledge, this is the first review to focus on deep learning architectures and their applications in the investment portfolio management problem. The review also presents a novel universal taxonomy of models used.

In past decades, artificial neural network (ANN) models have revolutionised various stock market operations due to their superior ability to deal with nonlinear data and garnered considerable attention from researchers worldwide. The present study aims to synthesize the research field concerning ANN applications in the stock market to a) systematically map the research trends, key contributors, scientific collaborations, and knowledge structure, and b) uncover the challenges and future research areas in the field.

To provide a comprehensive appraisal of the extant literature, the study adopted the mixed approach of quantitative (bibliometric analysis) and qualitative (intensive review of influential articles) assessment to analyse 1,483 articles published in the Scopus and Web of Science indexed journals during 1992–2022. The bibliographic data was processed and analysed using VOSviewer and R software.

The results revealed the proliferation of articles since 2018, with China as the dominant country, Wang J as the most prolific author, “Expert Systems with Applications” as the leading journal, “computer science” as the dominant subject area, and “stock price forecasting” as the predominantly explored research theme in the field. Furthermore, “portfolio optimization”, “sentiment analysis”, “algorithmic trading”, and “crisis prediction” are found as recently emerged research areas.

To the best of the authors’ knowledge, the current study is a novel attempt that holistically assesses the existing literature on ANN applications throughout the entire domain of stock market. The main contribution of the current study lies in discussing the challenges along with the viable methodological solutions and providing application area-wise knowledge gaps for future studies.

This study aims to investigate the impact of the COVID-19 pandemic on the time-frequency connectedness between green bonds, stock markets and commodities (Brent and Gold), with a particular focus on China and its implication for portfolio diversification across different frequencies.

To this end, the authors implement the frequency connectedness approach of Barunik and Krehlik (2018), followed by the network connectedness before and during the COVID-19 outbreak. In particular, the authors implement more involvement in portfolio allocation and risk management by estimating hedge ratios and hedging effectiveness for green bonds and other financial assets.

The time-frequency domain spillover results show that gold is the net transmitter of shocks to green bonds in the long run, whereas green Bonds are the net recipients of shocks, irrespective of time horizons. The subsample analysis for the pandemic crisis period shows that green bonds dominate the network connectedness dynamic, mainly because it is strongly connected with the SP500 index and China (SSE). Thus, green bonds may serve as a potential diversifier asset at different time horizons. Likewise, the authors empirically confirm that green bonds have sizeable diversification benefits and hedges for investors towards stock markets and commodity stock pairs before and during the COVID-19 outbreak for both the short and long term. Gold only offers diversification gains in the long run, while Brent does not provide the desired diversification gains. Thus, the study highlights that green bonds are only an effective diversified.

This study contributes to the existing literature by improving the understanding of the interconnectedness and hedging opportunities in short- and long-term horizons between green bonds, commodities and equity markets during the COVID-19 pandemic shock, with a particular focus on China. This study's findings provide more implications regarding portfolio allocation and risk management by estimating hedge ratios and hedging effectiveness.

Research and development (R&D) projects are often pursued through a project portfolio (PP). R&D PPs involve many stakeholders, and without proactive management, their interactions may lead to conflict risks. These conflict risks change dynamically with different stages of the PP life cycle, increasing the challenge of PP risk management. Existing conflict risk research mainly focuses on source identification but lacks risk assessment work. To better manage the stakeholder conflict risks (SCRs) of R&D PPs, this study employs the dynamic Bayesian network (DBN) to construct its dynamic assessment model.

This study constructs a DBN model to assess the SCRs in R&D PP. First, an indicator system of SCRs is constructed from the life cycle perspective. Then, the risk relationships within each R&D PPs life cycle stage are identified via interpretative structural modeling (ISM). The prior and conditional probabilities of risks are obtained by expert judgment and Monte Carlo simulation (MCS). Finally, crucial SCRs at each stage are identified utilizing propagation analysis, and the corresponding risk responses are proposed.

The results of the study identify the crucial risks at each stage. Also, for the crucial risks, this study suggests appropriate risk response strategies to help managers better perform risk response activities.

This study dynamically assesses the stakeholder conflict risks in R&D PPs from a life-cycle perspective, extending the stakeholder risk management research. Meanwhile, the crucial risks are identified at each stage accordingly, providing managerial insights for R&D PPs.

The purpose of this study is to conduct a systematic content review and bibliometric analysis of the current research trends, core concepts and knowledge mapping on the topic Islamic Banking and Finance (IBF) during Covid-19. Apart from highlighting the contributions of prolific authors, prominent institutions and countries, a comprehensive review of a significant number of documents using co-citation and co-word analysis is carried out for the science mapping.

A data set of 125 papers was collected published in Scopus database during the period December, 2019 and January 5th, 2023. Yearly publications, most-cited papers and authors, active sources, affiliations and countries are highlighted with descriptive analysis. Knowledge structure of the topic was mapped with investigating the social, intellectual and conceptual structures of IBF research. Content analysis is carried out to uncover the underlying research clusters that shape the scientific knowledge structure of studies.

A diverse group of authors and institutions contribute to the growing body of knowledge on the topic. IBF is adopting new paradigms and frameworks to integrate FinTech, crowd funding and Islamic social finance to provide sustainable solutions in both crisis and normal periods. The research on IBF is classified in to three themes: “financial markets in Covid-19,” “modeling risk and market regimes” and “FinTech and Islamic social finance.”

This study collects data only from Scopus database. Future studies must include research articles from other databases such as, Web of Sciences.

This study highlights research gaps in the existing literature and provides directions for future research.

This study investigates the diversification benefits of multiple cryptocurrencies and their usefulness as investment assets, individually or combined, in enhancing the performance of a well-diversified portfolio of traditional assets before and during the pandemic COVID-19.

This paper uses two optimization techniques, namely the mean-variance and the maximum Sharpe ratio. The naïve diversification rules are used for comparison. Besides, the Sharpe and the Sortino ratios are used as performance measures.

The results show that cryptocurrencies diversification benefits occur more during the COVID-19 pandemic rather than before it, with the maximum Sharpe ratio portfolio presenting its highest performance. Furthermore, the results suggest that, during COVID-19, the diversification benefits are slightly better when using a combination of cryptocurrencies to an already well-diversified portfolio of traditional assets rather than individual ones. This serves to improve the performance of the maximum Sharpe ratio portfolio, and to some extent, the naïve portfolio. Yet, cryptocurrencies, whether added individually or combined to a well-diversified portfolio of traditional assets, don't fit in the minimum variance portfolio. Besides, the efficient frontier during COVID-19 pandemic dominates the one before COVID-19 pandemic, giving the investor a better risk-return trade-off.

To the best of the author's knowledge, this is the first study that examines the diversification benefits of multiple cryptocurrencies both as individual investments and as additional asset classes, before and during COVID-19 pandemic. The paper covers all analyses performed separately in previous studies, which brings new evidence regarding the potential for cryptocurrencies in portfolio diversification under different portfolio strategies.

The purpose of this paper is to provide theory for some popular models and strategies used by practitioners in constructing optimal portfolios. King (2007), for example, advocated adding a diversification term to mean-variance problems to create better portfolios and provided clear empirical evidence that this is beneficial.

The authors provide an analytical framework to help us understand different portfolio construction practices that may incorporate diversification and conviction strategies; this allows us to connect our analysis to ideas in psychophysics and behavioural finance. The critical psychological ideas are cognitive dissonance and entropy; the economics are based on expected utility theory. The empirical section uses the theory outlined and provides the basis for constructing such portfolios.

The model presented allows the incorporation of different strategies within a mean-variance framework, ranging from diversification and conviction strategies to more ESG-oriented ones. The empirical analysis provides a practical application.

To the best of the authors’ knowledge, this model is the first to bridge the gap between portfolio optimisation and the psychological ideas mentioned in a coherent analytical framework.

By using higher moments, this paper extends the quadratic local risk-minimizing approach in a general discrete incomplete financial market. The local optimization subproblems are convex or nonconvex, depending on the moment variants used in the modeling. Inspired by Lai et al. (2006), the authors propose a new multiobjective approach for the combination of moments that is transformed into a multigoal programming problem.

The authors evaluate financial derivatives with American features using local risk-minimizing strategies. The financial structure is in line with Schweizer (1988): the market is discrete, self-financing is not guaranteed, but deviations are controlled and reduced by minimizing the second moment. As for the quadratic approach, the algorithm proceeds backwardly.

In the context of evaluating American option, a transposition of this multigoal programming leads not only to nonconvex optimization subproblems but also to the undesirable fact that local zero deviations from self-financing are penalized. The analysis shows that issuers should consider some higher moments when evaluating contingent claims because they help reshape the distribution of global cumulative deviations from self-financing.

A detailed numerical analysis that compares all the moments or some combinations of them is performed.

The quadratic approach is extended by exploring other higher moments, positive combinations of moments and variants to enforce asymmetry. This study also investigates the impact of two types of exercise decisions and multiple assets.

This paper proposes selecting a construction project portfolio in the context of a public institution, which makes it possible to assess quantitative and qualitative criteria, thereby meeting the needs of the institution and the existing constraints.

The research design follows a framework using technique for order preference by similarity to ideal solution (TOPSIS) associated with integer linear programming.

The method involves a flow of assessments allowing criteria and weights to be elicited where outcomes are based on the experts' intra-criteria assessment of alternatives and decision-makers' inter-criteria assessment. This is of utmost interest to public organizations, where selections must result in benefits and lower costs, integrating the experts' technical and management perspectives.

Public institutions are characterized by having limited financial and personnel resources for project development despite having a high demand for requests not associated with profits, making it essential to have a framework that enables using multiple criteria to better evaluate the benefits related to these decisions.

The main contributions of this article are: (1) the proposition of a framework for selecting construction project portfolios considering the organization's strategic needs; (2) identifying quantitative and qualitative assessment criteria for project selection; (3) integrating TOPSIS with an optimization process for selecting the construction project portfolios and (4) providing a structured decision process for selecting the portfolio that best represents the interests of the institution within its limited resources and personnel.

This paper proposes a two-level supply chain including suppliers and manufacturers. The purpose of this paper is to design a resilient fuzzy risk-averse supply portfolio selection approach with lead-time sensitive manufacturers under partial and complete supply facility disruption in addition to the operational risk of imprecise demand to minimize the mean-risk costs. This problem is analyzed for a risk-averse decision maker, and the authors use the conditional value-at-risk (CVaR) as a risk measure, which has particular applications in financial engineering.

The methodology of the current research includes two phases of conceptual model and mathematical model. In the conceptual model phase, a new supply portfolio selection problem is presented under disruption and operational risks for lead-time sensitive manufacturers and considers resilience strategies for risk-averse decision makers. In the mathematical model phase, the stages of risk-averse two-stage fuzzy-stochastic programming model are formulated according to the above conceptual model, which minimizes the mean-CVaR costs.

In this paper, several computational experiments were conducted with sensitivity analysis by GAMS (General algebraic modeling system) software to determine the efficiency and significance of the developed model. Results show that the sensitivity of manufacturers to the lead time as well as the occurrence of disruption and operational risks, significantly affect the structure of the supply portfolio selection; hence, manufacturers should be taken into account in the design of this problem.

The study proposes a new two-stage fuzzy-stochastic scenario-based mathematical programming model for the resilient supply portfolio selection for risk-averse decision-makers under disruption and operational risks. This model assumes that the manufacturers are sensitive to lead time, so the demand of manufacturers depends on the suppliers who provide them with services. To manage risks, this model also considers proactive (supplier fortification, pre-positioned emergency inventory) and reactive (revision of allocation decisions) resilience strategies.