Search results

This paper aims to propose an improved version of portfolio optimization model through the prediction of the future behavior of stock returns using a combined wavelet-based long short-term memory (LSTM).

First, data are gathered and divided into two parts, namely, “past data” and “real data.” In the second stage, the wavelet transform is proposed to decompose the stock closing price time series into a set of coefficients. The derived coefficients are taken as an input to the LSTM model to predict the stock closing price time series and the “future data” is created. In the third stage, the mean-variance portfolio optimization problem (MVPOP) has iteratively been run using the “past,” “future” and “real” data sets. The epsilon-constraint method is adapted to generate the Pareto front for all three runes of MVPOP.

The real daily stock closing price time series of six stocks from the FTSE 100 between January 1, 2000, and December 30, 2020, is used to check the applicability and efficacy of the proposed approach. The comparisons of “future,” “past” and “real” Pareto fronts showed that the “future” Pareto front is closer to the “real” Pareto front. This demonstrates the efficacy and applicability of proposed approach.

Most of the classic Markowitz-based portfolio optimization models used past information to estimate the associated parameters of the stocks. This study revealed that the prediction of the future behavior of stock returns using a combined wavelet-based LSTM improved the performance of the portfolio.

Optimum utilization of investments has always been considered one of the most crucial aspects of capital markets. Investment into various securities is the subject of portfolio optimization intent to maximize return at minimum risk. In this series, a population-based evolutionary approach, stochastic fractal search (SFS), is derived from the natural growth phenomenon. This study aims to develop portfolio selection model using SFS approach to construct an efficient portfolio by optimizing the Sharpe ratio with risk budgeting constraints.

This paper proposes a constrained portfolio optimization model using the SFS approach with risk-budgeting constraints. SFS is an evolutionary method inspired by the natural growth process which has been modeled using the fractal theory. Experimental analysis has been conducted to determine the effectiveness of the proposed model by making comparisons with state-of-the-art from domain such as genetic algorithm, particle swarm optimization, simulated annealing and differential evolution. The real datasets of the Indian stock exchanges and datasets of global stock exchanges such as Nikkei 225, DAX 100, FTSE 100, Hang Seng31 and S&P 100 have been taken in the study.

The study confirms the better performance of the SFS model among its peers. Also, statistical analysis has been done using SPSS 20 to confirm the hypothesis developed in the experimental analysis.

In the recent past, researchers have already proposed a significant number of models to solve portfolio selection problems using the meta-heuristic approach. However, this is the first attempt to apply the SFS optimization approach to the problem.

Increasing focus on socially responsible investments (SRIs) and green projects in recent times, coupled with the arrival of COVID pandemic, are the main drivers of this study. The authors conduct a post-factum analysis of investor choice between sin and green investments before and through the COVID outbreak.

A passive investor is introduced who seeks maximum risk-adjusted return and/or investment variance. When presented an opportunity to add sin and/or green investments to her initial one-asset market-only investment position, she views and handles this issue as a portfolio problem (MPT). She estimates value-at-risk (VaR) and conditional-value-at-risk (CVaR) for portfolios to account for downside risk.

Green investments offer better overall risk-return optimization in spite of major inter-period differences in return-risk dynamics and substantial downside risk. Portfolios optimized for minimum variance perform just as well as the ones optimized for minimum downside risk. Return and risk have settled at higher levels since the onset of COVID, resulting in shifting the efficient frontier towards north-east in the return-risk space.

The study contributes to the literature in two ways: One, it examines investor choice between sin and green investments during a global health emergency and views this choice against the one made during normal times. Two, instead of using the principles of modern portfolio theory (MPT) explicitly for diversification, the study uses them to identify investor preference for one over the other investment type. This has not been widely done thus far.

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.

Factor investment is booming in global asset management, especially environmental, social, and governance (ESG), dividend yield, and volatility factors. In this chapter, we use data from the US securities market from 2003 to 2019 to predict dividends and volatility factors through machine learning and historical data–based methods. After that, we utilize particle swarm optimization to construct the Markowitz portfolio with limits on the number of assets and weight restrictions. The empirical results show that that the prediction ability using XGBoost is superior to the historical factor investment method. Moreover, the investment performance of our portfolio with ESG, high-yield, and low-volatility factors outperforms baseline methods, especially the S&P 500 ETF.

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.

Purpose: The present study aims to test the Quadratic Programming model for Optimal Portfolio selection empirically.

Need for the Study: All the investors who buy financial products are motivated to obtain higher profits or, in other words, to maximise their returns. However, the high returns are often accompanied by higher risks, and avoiding such risks has become the primary concern for all investors. There is a great need for such a model to maximise profits and minimise risk, which can help design an investment portfolio with minimum risk and maximum return. The Quadratic Programming model is one such model which can be applied for selected shares to build an optimised portfolio.

Methodology: This study optimises the stock samples using a two-level screening of correlation coefficient and coefficient of variation. The monthly closing prices of the NSE-listed Indian pharmaceutical stocks from December 2019 to January 2022 have been used as sample data. The Lagrange Multiplier method is used to apply the model to achieve the optimal portfolio solution. Based on the market reality, the transaction costs have also been considered. The Quadratic programming model is further optimised to achieve the optimal portfolio for the select stocks.

Findings: The traditional portfolio theory and the modified quadratic model gives similar and consistent results. In other words, the modified quadratic model asserts the accuracy of the conventional portfolio model. The portfolio constructed in the present study gives a return much higher than the return of the benchmark portfolio of Nifty Fifty, indicating the usefulness of applying the Quadratic Programming model.

Practical Implications: The construction of an optimal portfolio using the traditional or modified Quadratic model can help investors make rational investment decisions for better returns with lower risks.

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.

This study aims to investigate the relationship between risks and the expected return of financial investment because the relationship between them is negative; if the investors agree to the higher level of risk, they have the greater the expected return; therefore, investors always require a degree of proportionality between the risks and returns.

This study applied the standard deviation, variance, coefficient of variation methods and matrix function to measure risks. Besides, the dataset is a return on equity ROE, which is collected in three companies at time series from 2005 to 2020.

When the variance or the standard deviation is higher, the return on the securities is higher, but the securities are a higher risk and vice versa. The results showed risk levels of stocks that are 2.509%, 0.367%, 3.666% and the corresponding return mean of 38.68%, 23.99% and 14.02%.

The results support the portfolio management policy appropriately. This study identifies issues for managers, investors and readers to consider: have a comprehensive solution among microcosmic policies, finance policy, investment policy and other policies to control and balance the relationship between risks and returns; have appropriate policies to regulate funds to stimulate investment in the long term.

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.