Search

Time series forecasting models are essential decision support tools in real-world domains. Stock market is a remarkably complex domain, due to its quickly evolving temporal nature, as well as the multiple factors having an impact on stock prices. To date, a number of machine learning-based approaches have been proposed in the literature to tackle stock trend prediction. However, they typically tend to analyze a single data source or modality, or consider multiple modalities in isolation and rely on simple combination strategies, with a potential reduction in their modeling power. In this paper, we propose a multimodal deep fusion model to predict stock trends, leveraging daily stock prices, technical indicators, and sentiment in daily news headlines published by media outlets. The proposed architecture leverages a BERT-based model branch fine-tuned on financial news and a long short-term memory (LSTM) branch that captures relevant temporal patterns in multivariate data, including stock prices and technical indicators. Our experiments on 12 different stock datasets with prices and news headlines demonstrate that our proposed model is more effective than popular baseline approaches, both in terms of accuracy and trading performance in a portfolio analysis simulation, highlighting the positive impact of multimodal deep learning for stock trend prediction. [ABSTRACT FROM AUTHOR]

Integration of asset preselection with appropriate portfolio optimization techniques can improve the performance of the portfolio optimization models. This paper morphed the potential asset selection and the optimal portfolio construction rather than focusing on one. A large volume of sample data from 25 stocks is used for the experiment from the National Stock Exchange, India, between January 2005 and December 2021. Initially, a 3-step screening approach, an asset selection method is applied to select potential assets. The 3-steps comprise data choice, fundamental screening, and the Long Short Term Memory model anticipating real-time stock prices to shortlist stocks with higher expected returns. The suggested approach is effective in determining the quality of assets. Further, the optimal asset allocation is done by introducing a novel exponentially weighted-mean-variance model. This exponential weighting scheme outperforms the classical Mean-Variance model when applied to the maximum Sharpe ratio model. The proposed model outperforms the five baseline techniques in terms of the Sharpe ratio and average potential returns and risks. Additionally, the proposed model's resilience across diversified time frames is tested through the incorporation of multiple time windows, demonstrating robustness of the performance. [ABSTRACT FROM AUTHOR]

In the face of changing investment intentions, the integration of environmental, social and governance (ESG) considerations into portfolio optimization is becoming the norm. Indeed, the purely financial dimension of investments is beginning to give way to the sustainable or responsible dimension which aims to generate long-term financial returns. Such an investment strategy has the constraint of investing only in companies which, according to the rating agencies, best meet these three criteria. To study the impact of similar investment strategies on portfolio performance, we compared the performance of 3 portfolios constructed with different ESG preferences. Built on the basis of the Best-in-class approach, the first is composed of the highest rated assets (AAA and AA) while the second has average ratings (A and BBB) and the third of the worst ESG ratings (BB, B and CCC). The results obtained in a robust mean-LPM theoretical framework, we managed to show that a preference for stocks with average ESG ratings in the composition of a portfolio to have the best risk-return trade-off. [ABSTRACT FROM AUTHOR]

This paper adopts the multi-criterion decision-making model of fuzzy-TODIM and genetic algorithm (GA) for optimal portfolio allocation. We applied Markowitz's portfolio parameters as inputs for the fuzzy TODIM model to rank stocks that are constituents of each index from three different markets. Portfolios are then generated dynamically using three weighting techniques and subject to multi-objective criteria and additional constraints. The results indicate a significant variation in performance metrics between the model-generated portfolios and the market indices. Replication of the procedure produces a similar outcome. Moreover, the out-of-sample tests conducted over 3 years validate the results' robustness, indicating that fuzzy TODIM, combined with GA, can achieve superior performance in dynamic portfolio allocation. [ABSTRACT FROM AUTHOR]

This paper empirically investigates the performance of portfolio screening strategies based on ESG (Environmental, Social, Governance) scores, by testing three main hypotheses motivated by the introduction of sustainability considerations within portfolio theory: i) ESG screened portfolios overperform the benchmark in the long term only if the exclusion threshold is low; ii) ESG screened portfolios do not overperform the benchmark in the short term independently of the exclusion threshold; iii) ESG screened portfolios overperform the benchmark in terms of systemic risk in periods of financial distress. To this end, negative and positive screening strategies based on Bloomberg ESG disclosure scores and different screening thresholds are set up from the 559 stocks belonging to the EURO STOXX index in the period 2007–2021. The risk-adjusted performance of the ESG screened portfolios is compared with the benchmark-passive one based on Sharpe Ratio (SR) and alphas (from both a one-factor model and the Carhart four-factor model) so as to test performance over total and systemic risk respectively. Two main results emerge. First, we prove overperformance of screened portfolios only in the long run and in the presence of negative screening strategies with a low screening threshold. Second, we do not find clear evidence of over-compensation for systemic risk in all periods of financial distress, thus the alleged safe-haven property of ESG portfolios is not always there. Given the increasing attention for sustainability, our results have relevant implications for both individual investors and the asset management industry. [ABSTRACT FROM AUTHOR]

Artificial intelligence techniques for financial time series analysis have been used to enhance momentum trading methods. However, most previous studies, which have treated stocks as independent entities, have overlooked the significance of correlations among individual stocks, thus compromising portfolio performance. To address this gap, a momentum trading framework is proposed that combines heterogeneous data, such as corporate governance factors and financial domain knowledge, to model the relationships between stocks. Our approach involves adopting a knowledge graph embedding approach to map relations among heterogeneous relationships in the data, which is then utilized to train a multitask supervised learning approach based on a learning-to-rank algorithm. This method culminates in a robust portfolio selection method on the basis of the framework. Experimental results using data from the Taiwan Stock Exchange demonstrate that our proposed method outperforms traditional linear models and other machine learning methods in predictive ability. The investment portfolio constructed serves as an invaluable aid to investment decision-making. [ABSTRACT FROM AUTHOR]

Algorithm portfolios are multi-algorithmic schemes that combine a number of solvers into a joint framework for solving global optimization problems. A crucial part of such schemes is the resource allocation process that is responsible for assigning computational resources to the constituent algorithms. We propose a resource allocation process based on adaptive decision-making procedures. The proposed approach is incorporated in algorithm portfolios composed of three essential types of numerical optimization algorithms, namely gradient-based, direct search, and swarm intelligence algorithms. The designed algorithm portfolios are experimentally demonstrated on a challenging optimization problem for different dimensions and experimental settings. The accompanying statistical analysis offers interesting conclusions and insights on the performance of the algorithm portfolio compared to its constituent algorithms, as well as on the effect of its parameters. [ABSTRACT FROM AUTHOR]

People usually create a portfolio in order to diversify the risk coming from individual investments. To get a high yield with a good level of diversification, investors usually seek professional advice from portfolio managers. However, the true performance of an optimized portfolio usually depends on the correctness of the estimates of the distribution of future returns, which is often a matter of luck rather than skill. Thus, the optimization models may not be better than randomly selected portfolios. Our aim is to find how the so-called strategy portfolios, i.e., portfolios obtained by some decision optimized for a long-run horizon, perform compared to a benchmark, namely, a random investment, under specific market conditions. For this purpose, we evaluate several portfolio strategies over two periods of crisis: the subprime mortgage crisis and the Covid-19 pandemic, as well as run a moving window analysis over a longer horizon. In each case, the results are compared with the performance of random-weight portfolios. We find that if the strategy is minimization, the portfolios perform well; however, for the maximization of the objectives, the results are rather mixed. [ABSTRACT FROM AUTHOR]

Noise is an important factor affecting portfolio performance, how to construct an effective denoising strategy is becoming increasingly important for investors. In this study, we theoretically explain the impact of noise on portfolio and argue the necessity of denoising. Next, the empirical mode decomposition (EMD) denoising strategy based on the correlation coefficient test criterion is proposed to improve portfolio performance. In detail, EMD is used to decompose the noisy price, then, a series of correlation coefficient tests are performed to determine which intrinsic mode functions (IMFs) are noise. In the empirical analysis, we apply the proposed method to denoise the SSE 50 index's constituents, and further test the out-of-sample performance under the mean–variance framework. The empirical results show that the proposed denoising method outperforms four common EMD, Ensemble EMD (EEMD) and wavelet denoising methods in return-risk ratio. The proposed method is the optimal denoising strategy, which can help investors improve portfolio performance to the greatest extent. [ABSTRACT FROM AUTHOR]

We investigate the performance of VaR (Value at Risk) forecasts, considering different multivariate models: HS (Historical Simulation), DCC-GARCH (Dynamic Conditional Correlation-Generalized Autoregressive Conditional Heteroskedasticity) with normal and Student's t distribution, GO-GARCH (Generalized Orthogonal-Generalized Autoregressive Conditional Heteroskedasticity), and copulas Vine (C-Vine, D-Vine, and R-Vine). For copula models, we consider that marginal distribution follow normal, Student's t and skewed Student's t distribution. We assessed the performance of the models using stocks belonging to the Ibovespa index during the period from January 2012 to April 2022. We build portfolios with 6 and 12 stocks considering two strategies to form the portfolio weights. We use a rolling estimation window of 500 and 1000 observations and 1%, 2.5%, and 5% as significance levels for the risk estimation. To evaluate the quality of the risk forecasts, we compute the realized loss and cost. Our results show that the performance of the models is sensitive to the use of different significance levels, rolling windows, and strategies to determine portfolio weights. Furthermore, we find that the model that presents the best trade-off between the costs from risk overestimation and underestimation does not coincide with the model suggested by the realized loss. [ABSTRACT FROM AUTHOR]

Effective denoising strategies are increasingly important for portfolio investors. Considering that the common ensemble empirical mode decomposition (EEMD)-based stepwise denoising algorithms suffer from white noise interference and ignore the effect of low-frequency redundant noise components on the portfolio, a novel complete EEMD with adaptive noise (CEEMDAN) denoising algorithm is proposed to improve the portfolio performance. Specifically, we apply CEEMDAN to decompose noisy prices into a series of intrinsic mode functions (IMFs). Then, a series of tests based on the correlations between the original noisy prices and the decomposed IMFs are performed to identify which IMFs are noisy modes. If the tests accept the null hypothesis, the IMFs are considered as noisy components. Finally, we use the soft-threshold technique to process the noisy components and sum the non-noisy components to construct the denoised prices. The empirical results show that under the dynamic minimum-CVaR framework, the proposed CEEMDAN denoising algorithm is not affected by white noise and outperforms the EEMD denoising and stepwise denoising algorithms in improving out-of-sample portfolio returns. Overall, the proposed CEEMDAN denoising is the optimal denoising algorithm, which can help investors improve portfolio performance to the greatest extent. [ABSTRACT FROM AUTHOR]

The range of non-EPS forecast types provided by individual analysts to I/B/E/S has increased dramatically over time but varies considerably across firms. We propose that in providing a broader range of forecast types, analysts can signal superior research ability and research effort. Consistent with this hypothesis, we document positive associations between the number of forecast types (NFT) an analyst provides and common proxies for research quality, including earnings forecast accuracy, price target accuracy, stock recommendation profitability, market reactions to stock recommendation revisions, and analyst career outcomes. The effects of NFT are incremental to other quality proxies used in the literature and are distinct from the issuance of specific non-EPS forecast types studied previously (e.g., cash flow forecasts). We demonstrate the information value of NFT to investors by examining the out-of-sample performance of portfolios formed conditional on NFT and exploiting revisions in consensus earnings forecasts and individual analysts' stock recommendations. We conclude that the number of forecast types an analyst provides for a firm is a readily available proxy for the quality of her research. [ABSTRACT FROM AUTHOR]

The objectives of this study are to analyze the presence of environmental values in ESG indexes based on the positive value relationship between energy and the environment found in existing studies and to identify the characteristics of environmental, social, and governance (ESG) investments by examining the performance of ESG investments compared to market portfolios, as well as to consider the implications of ESG investment in clean energy policy based on the results of the empirical analysis of this study. This paper contributes threefold. First, using a supply and demand-based pricing model, we propose a new model of the expected return, risk, and performance ratio of the ESG premiums defined by the log price differences between ESG indexes and a market portfolio to analyze how ESG investments perform. Second, based on the empirical findings of this study that the correlation between ESG indexes and energy prices is a decreasing function of the latter in contrast to other environmental assets, this paper suggests that ESG indexes cannot adequately demonstrate environmental values but reflect social and governance values, i.e., (E)SG, in the complementary perspective. Third, using the empirical findings of this study that the information ratio of the ESG premium tends to be positive but declines and approaches zero over time, this paper indicates that although ESG investments can be significant compared to market index investments, the significance is limited because ESG investment performance converges with market portfolio performance. In conclusion, two points should be noted about ESG investing in clean energy policy: given the dilution of environmental values in ESG investing, a clear distinction should be made between ESG investing and renewable energy investing; even if investments in renewable energy projects are treated as ESG investments, reflecting current market trends, we should be prepared for the fact that the superior investment performance due to social and governance values, rather than environmental values, will not last long. [ABSTRACT FROM AUTHOR]

Stock markets are flooded with various uncertainties such as stock market scenarios, especially the input parameters of stock portfolio models. It is hard for stock market investments to jointly deal with them. Although robust portfolio is the prevailing portfolio policy handling with uncertainties, it always focuses on the worst-case scenario of all the possible realizations of uncertain input parameters, resulting in the optimal portfolios considerably conservative as well as the portfolio performances very inferior. To this end, based on Markowitz's mean–variance (MV) model, this paper builds the new robust portfolio model (RMV-best) from the innovative perspective of best-case scenario, exactly contrary to the model based on the worst-case scenario (RMV-worst). Furthermore, stock market scenarios which always shift uncertainly show the periodic characteristics, and can be divided into three movement statuses: the bull, the bear and the steady. To verify the consistency of RMV-best, RMV-worst and MV portfolio policies over the different motion periods and identify the differences of these portfolio policies at various movement statuses, the mix data including two motion periods and three industry sectors is employed. Eventually, empirical results indicate that RMV-best is always the most favorable portfolio policy at the bull and the bear market, while MV can produce more profitable portfolios at the steady market over two motion periods. However, the drawbacks of RMV-worst are also confirmed in this study. [ABSTRACT FROM AUTHOR]

We study market-to-book ratios of stocks in the context of stochastic portfolio theory. Functionally generated portfolios that depend on auxiliary economic variables other than relative capitalisations ("sizes") are developed in two ways, together with their relative returns with respect to the market. This enables us to identify the value factor (i.e., market-to-book ratio) in returns of such generated portfolios when the auxiliary variables are stocks' book values. Examples of portfolios, as well as their empirical results, are given, with the evidence that in addition to size, the value factor does affect the performance of the portfolio. [ABSTRACT FROM AUTHOR]

We investigate whether the display of portfolio performance as coming from one large portfolio or two smaller subportfolios matters to individuals and whether prospect theory can explain this preference. To this end, we run a large survey experiment of 3267 individuals in 5 European countries presenting an identical overall return as coming from one portfolio or two smaller subportfolios to individuals. We also elicited the coefficients of the prospect theory value function through price list lotteries. In losses, following prospect theory and mental accounting predictions, we observe emprically a preference for the display of returns as coming from 2 subportfolios, one displaying a small gain and the other a large loss, over a unique portfolio displaying the aggregated resulting loss. As expected, for an overall gain, individuals favor one portfolio over two subportfolios, one displaying a small loss and the other a larger gain. The shape of the value function does not explain individuals' preferences. The reference point seems to be the main factor involved in explaining individuals' choice of two subportfolio presentations of the outcome. [ABSTRACT FROM AUTHOR]

To the extent that a property portfolio is dependent on a small number of tenants for a large proportion of rental revenue, the portfolio has a concentrated tenant base. This article investigates the impact of tenant concentration on property portfolio performance, risk, and the cost of debt. Utilizing the disclosure of major tenants by 152 Equity Real Estate Investment Trusts (REITs) from 2000 to 2017, I document a positive relation between tenant concentration and profitability. REITs with greater tenant concentration experience higher profit margins and lower expense ratios, suggesting the positive relation between tenant concentration and profitability is driven by increased operational efficiency. Although these REITs are more efficient, tenant concentration is often stated as a risk in public disclosures. Consistent with this view, I find that REITs with greater tenant concentration have greater idiosyncratic risk. Further, banks appear to price this risk into their rate setting process and penalize REITs with greater tenant concentration. Accounting for the quality of the tenant base, the positive effects of tenant concentration are prevalent in REITs with high quality tenants and the negative effects of tenant concentration are prevalent REITs with low quality tenants. [ABSTRACT FROM AUTHOR]

We analyze whether cross-national distance between professional money managers and the positions they take in foreign markets affects investment performance. Out of four dimensions of cross-national distance (geography, culture, business climate, and industry), we find that only cultural distance inversely relates to portfolio performance. Investors earn higher returns in culturally similar foreign markets when market conditions in these countries are favorable. Our results show that the culture-based patterns in foreign portfolio allocations are associated with an information advantage and suggest that multinational corporate decisions influenced by culture increase firm value. [ABSTRACT FROM AUTHOR]

Based on the data of China's open-end stock funds and partial stock funds from 2009 to 2020, we take the implementation of green credit guidelines (GCG) as a quasi-natural experiment and investigate the impact of green credit policies on the net value crash risks of fund holding heavily polluting enterprise stocks. The results show that green credit policies will significantly increase the net value crash risks of fund holding heavily polluting enterprise stocks. Green credit policies increase the net value crash risks of fund holding heavily polluting enterprise stocks by increasing investor redemptions. Further tests show that better fund performance and higher portfolio concentration weaken the positive impact of green credit policies on the net value crash risks of fund holding heavily polluting enterprise stocks, and higher proportion of institutional investors strengthens the positive impact of green credit policies on the net value crash risks of fund holding heavily polluting enterprise stocks. This study supplements the literature on green credit policies and funds, and provides policy guidance for regulators. [ABSTRACT FROM AUTHOR]

This study examines the portfolio optimization problem by exploiting daily data of 10 international Exchange Trade Funds (ETF) from 2012 to 2022. We extend the Black-Litterman (BL) approach using ARMA-GARCH-copula-based expected returns as a proxy for investor views and use the CVaR metric as a risk measure in the optimization procedure. The BL approach provides a Bayesian methodology for combining the equilibrium returns and the investor views to produce expected returns. We use Regular Vine (R-vine) copula since it provides a flexible multivariate dependency modeling. The suggested approach is compared against the copula-CVaR portfolio, which likewise a BL copula approach avoids excessive corner solutions that many optimization approaches would generate in case of extreme values of estimated parameters. We compare the performance of these two approaches using out-of-sample back-testing against two benchmarks: Mean–Variance optimizations (MV) and equal weights portfolio (EW). To further reduce the sensitivity of considered strategies to input parameters, we evaluate out-of-sample performance at three levels of maximum weight constraints: 30%, 40%, and 50%. Moreover, in this paper, we consider different levels of view confidence—τ in the Black-Litterman model as it significantly affects the obtained results and inferences. We calculate and report the portfolios' tail risks, maximum drawdown, turnover, and the break-even point for all optimization approaches. Our empirical analysis indicates better performance for the CBL portfolio regarding lower tail risk and higher risk-adjusted returns, and the copula-CVaR portfolio is better regarding lower turnover and higher break-even point. [ABSTRACT FROM AUTHOR]

Risk management is an important aspect of financial research because correlations among financial data are essential in evaluating portfolio risk. Among various correlations, spatiotemporal correlations involve economic entity attributes and are interrelated in space and time. Such correlations have therefore drawn increasing attention in financial risk management. However, classical correlation measurements are typically based on either time series correlations or spatial dependence; they cannot be directly applied to financial data with spatiotemporal correlations. The spatiotemporal correlation coefficient model with adaptive weight proposed in this paper can (1) address the absolute quantity, dynamic quantity, and dynamic development of financial data and (2) be used for risk grading, financial risk evaluation, and portfolio management. To verify the validity and superiority of this model, cluster analysis results and portfolio performance are compared with a classical model with time series correlation or spatial correlation, respectively. Empirical findings show that the proposed coefficient is highly effective and convenient compared to others. Overall, our method provides a highly efficient financial risk management method with valuable implications for investors and financial institutions. [ABSTRACT FROM AUTHOR]

We present a detailed study of portfolio optimization using different versions of the quantum approximate optimization algorithm (QAOA). For a given list of assets, the portfolio optimization problem is formulated as quadratic binary optimization constrained on the number of assets contained in the portfolio. QAOA has been suggested as a possible candidate for solving this problem (and similar combinatorial optimization problems) more efficiently than classical computers in the case of a sufficiently large number of assets. However, the practical implementation of this algorithm requires a careful consideration of several technical issues, not all of which are discussed in the present literature. The present article intends to fill this gap and thereby provides the reader with a useful guide for applying QAOA to the portfolio optimization problem (and similar problems). In particular, we will discuss several possible choices of the variational form and of different classical algorithms for finding the corresponding optimized parameters. Viewing at the application of QAOA on error-prone NISQ hardware, we also analyse the influence of statistical sampling errors (due to a finite number of shots) and gate and readout errors (due to imperfect quantum hardware). Finally, we define a criterion for distinguishing between 'easy' and 'hard' instances of the portfolio optimization problem. [ABSTRACT FROM AUTHOR]

GARCH-EVT-Copula is proved to have some advantages in improving the accuracy of predicting returns. Investor sentiment described by four indicators (market-turnover ratio, advance-decline ratio, new-highs/lows ratio, and Arms index) attracts increasing attention from researchers. In view of these two factors, firstly, we construct the ARMA-GARCH-Sent (AGS) model with investor sentiment indicator by principal component analysis (PCA). Secondly, considering the advantages of extreme value theory (which can deal with extreme deviations in the value of the probability distribution), we present the ARMA-GARCH-Sent-EVT (AGSE) model to describe the daily logarithmic return series of stocks. In addition, the Copula model is used to construct the multivariate distribution of daily logarithmic stock return series to capture their asymmetric and nonlinear characteristics. Furthermore, we propose an ARMA-GARCH-Sent-EVT-Copula (AGSEC) portfolio model with Copula. In order to highlight the advantages of our model, we make a comparative analysis of three models: the original ARMA-GARCH-Copula (AGC) model, the ARMA-GARCH-Sent-Copula (AGSC) model and the AGSEC model. Finally, we use the data of SHSE (Shanghai Stock Exchange) and SZSE (Shenzhen Stock Exchange) for empirical analysis and compare the dynamic portfolio strategies of the three models. The results show that our model AGSEC with investor sentiment is superior to the other two models, namely, it has higher return rates under the same constraint conditions, which means investor sentiment can assist investors in better navigating market dynamics and plays an increasingly important role in shaping portfolio performance and risk management. [ABSTRACT FROM AUTHOR]

Choosing the greatest investment possibilities to maximize the value of one’s stock investment has always been one of the primary concerns of investors. However, issues like human rights, and business ethics, are at the forefront of the public and political conversation in today’s world of globalization and interdependence. Many financial experts, policymakers, and economic and social researchers view Islamic finance as a potential solution to prevent future crises. Consequently, there is a need for new models to facilitate this investment approach. In this study, we propose a new hybrid approach to portfolio selection which combines multiple methodologies like investor topology, cluster analysis, preference modeling and fuzzy multi-objective programming strategy. The proposed model is applied on 9 Tunisian mutual funds including conventional and ethical/Islamic funds in Tunisian financial market. The findings reveal that higher expected losses and greater proportions of ethical or Islamic stocks in a portfolio translate into better portfolio performance as measured by the Sharpe ratio. These findings confirm our hypothesis that ethical investments should be taken into account when developing investment strategies for conventional investors. [ABSTRACT FROM AUTHOR]

The Real Estate Investment Trust (REIT) market has become an increasingly important vehicle for alternative investment for equity investors. While existing research examining the cross-section of REIT returns usually employs standard risk factors in the in-sample models, it can only show the ex-post performance of REIT portfolios. The goal of our paper is to examine the ex-ante performance of REIT portfolios (i.e., the ability of investors to earn abnormal returns in real time). We employ the out-of-sample methodology of Cooper, Gutierrez, and Marcum (2005), and show that ex-ante performance of REIT portfolios is rather weak. For about half of our 19-year sample over the period of 1999 to 2017, the portfolio performances of REITs chosen ex-ante do not beat the performances of the FTSE-NAREIT or the CRSP Equal-Weighted index. After adjusting for transaction costs, the REIT portfolios significantly further underperform their benchmarks. Overall, our findings suggest that the market is relatively efficient in the REIT sector, and it is difficult for investors to devise trading strategies that improve the ex-ante performance of REIT portfolios, based on standard risk factors. [ABSTRACT FROM AUTHOR]

Discussion about the effect of constraints in portfolio selection is a popular topic in finance. In this paper, we test the portfolio performance under the existence of regulatory constraints. This paper tries to provide evidence of whether the existence of regulatory constraints translates into a better long-term performance of investment funds, one of the most important investment vehicles for citizens. We show the returns and their relationship with the portfolio's risk, compared to the same set without the usage of these constraints. The results state that, when using regulation as the constraining factor, we obtain more efficient portfolios. [ABSTRACT FROM AUTHOR]

This paper studies stochastic linear-quadratic control with a time-inconsistent objective and worst-case drift disturbance. We allow the agent to introduce disturbances to reflect her uncertainty about the drift coefficient of the controlled state process. We adopt a two-step equilibrium control approach to characterize the robust time-consistent controls, which can preserve the order of preference. Under a general framework allowing random parameters, we derive a sufficient condition for equilibrium controls using the forward-backward stochastic differential equation approach. We also provide analytical solutions to mean-variance portfolio problems for various settings. Our empirical studies confirm the improvement in portfolio's performance in terms of out-of-sample Sharpe ratio by incorporating with robustness. [ABSTRACT FROM AUTHOR]

We study the relationship between corporate social performance and financial performance by comparing the portfolio returns of firms with changes in corporate social responsibility (CSR) intensity. Using an extensive US sample from the MSCI ESG database, we find that improvement in the overall CSR is generally value enhancing. The relationship varies with CSR dimensions. More importantly, the relationship shifts differently for various CSR dimensions during the crisis period when trust in the society is low and financial resource is limited. Improvement in environment, human rights, and product characteristics shows higher financial returns during the financial crisis period, whereas the value enhancement of improvement in employee relations is more pronounced during the non-crisis period. [ABSTRACT FROM AUTHOR]

The dynamics of financial time series display a cyclical behavior, and the performance of portfolio decisions based on the anticipated distribution of asset returns are sensitive to the alignment of the anticipated distribution and subsequently observed returns in cyclical markets. We consider that the financial market is characterized by factors, and we present a regime-switching auto-regressive model for macro-economic factors to reflect financial cycles. We then define a factor model for the distribution of asset returns, with returns depending on regimes through the factors. The dependence is on the regime sequence in successive periods, or the regime transition. The factor model structure is embedded in the asset expected returns and their corresponding covariance matrix. These regime-dependent parameters serve as the inputs to mean-variance optimization, thereby constructing portfolios adapted to the current market environment. A contrast between investment decisions based on the expectation over regimes or the selection of a single most likely (inferred) regime is provided. The improvements in portfolio performance are calibrated with market data on macroeconomic factors and exchange traded funds as investment instruments. [ABSTRACT FROM AUTHOR]

We introduce hereafter a new flexible meta-measurement of portfolio performance, called the Generalized Utility-based N-moment measure, relying both on a characterization of the whole return distribution and on the set of preferences of the investor, which is adapted to analyze the performance of hedge funds. It could also serve as the basis of a Fraudulent Behavior Index aiming to detect fraudulent funds. [ABSTRACT FROM AUTHOR]

Financial models are based on the standard assumptions of frictionless markets, complete information, no transaction costs and no taxes and borrowing and short selling without restrictions. Short-selling bans around the world after the global financial crisis and in several exchanges during the COVID 19 period, become more and more important. This paper bridges the gap by providing for the first time in the literature a model that accounting explicitly and simultaneously for inflation, information costs and short sales in the portfolio performance with regime switching. Our model can be used by portfolio managers to assess the impact of these market imperfections on portfolio decisions. [ABSTRACT FROM AUTHOR]

This paper investigates the performance of Islamic fundamental weighted (FW) portfolios compared to that of non-Islamic counterparts, to examine whether Shari'ah-compliant stocks can protect investors during crises in the Middle East and North Africa region. Portfolios' performance is assessed using several risk-adjusted performance measures including more robust measures in the context of recently developed multi-factor models. The study's findings suggest that the performance of Islamic and non-Islamic FW portfolios depends on the performance measures used and on the periods under analysis. Both Islamic and non-Islamic FW portfolios underperform against the cap-weighted benchmark. Furthermore, the Islamic portfolios underperform compared to their non-Islamic counterparts during the period of the global financial crisis, while they perform similarly to their non-Islamic counterparts during the Arab Spring period. Based on these results, we conclude that Islamic FW portfolios do not seem to protect investors from losses during crises. [ABSTRACT FROM AUTHOR]

The purpose of this article is to evaluate optimal expected utility risk measures (OEU) in a risk-constrained portfolio optimization context where the expected portfolio return is maximized. We compare the portfolio optimization with OEU constraint to a portfolio selection model using value at risk as constraint. The former is a coherent risk measure for utility functions with constant relative risk aversion and allows individual specifications to the investor's risk attitude and time preference. In a case study with three indices, we investigate how these theoretical differences influence the performance of the portfolio selection strategies. A copula approach with univariate ARMA-GARCH models is used in a rolling forecast to simulate monthly future returns and calculate the derived measures for the optimization. The results of this study illustrate that both optimization strategies perform considerably better than an equally weighted portfolio and a buy and hold portfolio. Moreover, our results illustrate that portfolio optimization with OEU constraint experiences individualized effects, e.g., less risk-averse investors lose more portfolio value in the financial crises but outperform their more risk-averse counterparts in bull markets. [ABSTRACT FROM AUTHOR]

Prior research shows that noisy prices can introduce biases in returns causing equal-weighted portfolios to outperform value-weighted portfolios. In this paper, we reevaluate the superiority of EW portfolios in the presence of market frictions. We find that trading costs have limited impact on the performance of EW portfolios, while taxes cause the performance of both EW and VW portfolios to deteriorate by a similar magnitude leaving the superiority of EW portfolios intact. Besides mispricing, the results for small cap portfolios may also be affected by the size effect. Overall, EW portfolios earn annualized risk-adjusted returns between 1.23% and 1.79% even after accounting for trading costs and taxes. [ABSTRACT FROM AUTHOR]

This study investigates the conditions under which host country portfolios are more likely to regularize corporate tax behavior. We use a sample comprising data on Japanese multinationals covering 2004 to 2014 to examine the relationship between foreign direct investment (FDI) host country portfolios and tax avoidance from the perspectives of investor protection and ethical standards. Our multivariate regression results show that the number of countries with strong investor protection/high ethical standards in the FDI host country portfolio is negatively related to tax avoidance. We also find that the effect of investor protection/ethical standards is less pronounced when the degree of indulgence is high. Further analyses show that the relationships we find are affected by disclosure requirements, local regulations, and accounting standards. These findings remain unchanged after several sensitivity checks. Overall, this study contributes to the business ethics literature by showing that FDI host country investor protection and ethical standards are external monitoring mechanisms for mitigating tax avoidance by multinationals. [ABSTRACT FROM AUTHOR]

In this paper, distributionally robust mean-HMCR (higher moment coherent risk) portfolio optimization model based on kernel density estimation (KDE) and ϕ -divergence is proposed. In order to overcome the so-called "curse of dimensionality", we consider the one-dimensional probability distribution of the portfolio return, rather than the joint probability distribution of the assets return vector. The two issues of "the distribution dependent on the decision variables" and "the metric-based distributional uncertainty set for the continuous distribution" are effectively addressed by using the finite dimensional KDE based probability distribution. Under the mild conditions of the kernel function and ϕ -divergence function, the tractable reformulation of the corresponding distributionally robust optimization model is derived by Fenchel's Duality Theorem. Moreover, the convergence of optimal value and solution set of the KDE mean-HMCR distributionally robust portfolio optimization problem to those of the corresponding stochastic optimization model with the real distribution is proved. We conduct some empirical tests with the rolling horizon approach and compare the performance of the optimal portfolio strategy obtained by the proposed model to other three strategies by four performance criteria and their cumulative wealth curves. Empirical test results show that the quality of the portfolio strategy obtained by the proposed model is better at most cases. We also conduct empirically sensitivity analysis of model parameters. [ABSTRACT FROM AUTHOR]

In this work, the pricing problem of a variable annuity (VA) contract embedded with a guaranteed lifelong withdrawal benefit (GLWB) rider has been considered. VAs are annuities whose value is linked with a sub-account fund consisting of bonds and equities. The GLWB rider provides a series of regular payments to the policyholder during the policy duration when he is alive irrespective of the portfolio performance. Also, the remaining fund value is given to his nominee, at the time of death of the policyholder. The appropriate modelling of fund plays a crucial role in the pricing of VA products. In the literature, several authors model the fund value in a VA contract using a geometric Brownian motion (GBM) model with a constant variance. However, in real life, the financial assets returns are not Normal distributed. The returns have non-zero skewness, high kurtosis, and leverage effect. This paper proposes a discrete-time model for annuity pricing using generalized autoregressive conditional heteroscedastic (GARCH) models, which overcome the limitations of the GBM model. The proposed model is analyzed with numerical illustration along with sensitivity analysis. [ABSTRACT FROM AUTHOR]

We extend the analysis of investment strategies derived from penalized quantile regression models, introducing alternative approaches to improve state– of– art asset allocation rules. We make use of the post– model– selection estimation, which builds on two important choices: the specification of the penalty function and the selection of the optimal tuning parameter. Therefore, we first investigate whether and to what extent the performance of a given portfolio changes when moving from convex to nonconvex penalty functions. Second, we compare different methods to select the optimal tuning parameter, which controls the intensity of the penalization. Empirical analyses on real– world data show that these alternative methods outperform the standard LASSO, providing improvements in terms of risk, risk– adjusted return and portfolio concentration. This evidence becomes stronger when focusing on extreme risk, which is strictly linked to quantile regression. [ABSTRACT FROM AUTHOR]

Google search volumes have proven to be useful in portfolio management. The basic idea is that high search volumes are related to bad news and risk increase. This paper shows additional evidence about the use of Google search volumes in risk management, for the Dow Jones Industrial Average index components from 2004 to 2017. To overcome the (time-series and cross-section) limitations Google imposes on data download, a renormalization procedure is presented, to obtain a multivariate sample of volumes, which preserve their relative magnitude. The results indicate that the volume normalization is relevant for portfolio performances. Renormalized Google search volumes yield poor results when they penalize the portfolio diversification. Instead, if the portfolio diversification can be kept to an acceptable level, the renormalized Google search volumes contribute to improving risk-adjusted performances. [ABSTRACT FROM AUTHOR]

This paper investigates an elliptic entropy of uncertain random variables and its application in the area of portfolio selection. We first define the elliptic entropy to characterize the uncertainty of uncertain random variables and give some mathematical properties of the elliptic entropy. Then we derive a computational formula to calculate the elliptic entropy of function of uncertain random variables. Furthermore, we use the elliptic entropy to characterize the risk of investment and establish a mean-entropy portfolio selection model, in which the future security returns are described by uncertain random variables. Based on the chance theory, the equivalent form of the mean–entropy model is derived. To show the performance of the mean–entropy portfolio selection model, several numerical experiments are presented. We also numerically compare the mean–entropy model with the mean–variance model, the equi-weighted portfolio model, and the most diversified portfolio model by using three kinds of diversification indices. Numerical results show that the mean-entropy model outperforms the mean–variance model in selecting diversified portfolios no matter of using which diversification index. [ABSTRACT FROM AUTHOR]

We report a dynamic programming algorithm which, given a set of efficient (or even inefficient) portfolios, constructs an optimal portfolio trading strategy that maximizes the probability of attaining an investor's specified target wealth at the end of a designated time horizon. Our algorithm also accommodates periodic infusions or withdrawals of cash with no degradation to the dynamic portfolio's performance or runtime. We explore the sensitivity of the terminal wealth distribution to restricting the segment of the efficient frontier available to the investor. Since our algorithm's optimal strategy can be on the efficient frontier and is driven by an investor's wealth and goals, it soundly beats the performance of target date funds in attaining investors' goals. These optimal goals-based wealth management strategies are useful for independent financial advisors to implement behavioral-based FinTech offerings and for robo-advisors. [ABSTRACT FROM AUTHOR]

In this paper we consider a portfolio selection problem under the global minimum variance model where the optimal portfolio weights only depend on the covariance matrix of asset returns. First, to reflect the rapid changes of financial markets, we incorporate a time-varying factor in the covariance matrix. Second, to improve the estimation of the covariance matrix we use the shrinkage method. Based on these two key aspects, we propose a framework for shrinking the time-varying inverse conditional covariance matrix in order to enhance the performance of the portfolio selection. Furthermore, given the shortcoming that the inverse covariance matrix is inaccurate in a number of cases, we develop a new method that transforms the inverse of the covariance matrix into a product to improve the performance of the inverse covariance matrix, and prove its theoretical availability. The proposed portfolio selection strategy is applied to analyze real-world data and the numerical studies show it performs well. [ABSTRACT FROM AUTHOR]

Certain literature that constructs a multifactor stock selection model adopted a weighted-scoring approach despite its three shortcomings. First, it cannot effectively identify the connection between the weights of stock-picking concepts and portfolio performances. Second, it cannot provide stock-picking concepts' optimal combination of weights. Third, it cannot meet various investor preferences. Thus, this study employs a mixture experimental design to determine the weights of stock-picking concepts, collect portfolio performance data, and construct performance prediction models based on the weights of stock-picking concepts. Furthermore, these performance prediction models and optimization techniques are employed to discover stock-picking concepts' optimal combination of weights that meet investor preferences. The samples consist of stocks listed on the Taiwan stock market. The modeling and testing periods were 1997–2008 and 2009–2015, respectively. Empirical evidence showed (1) that our methodology is robust in predicting performance accurately, (2) that it can identify significant interactions between stock-picking concepts' weights, and (3) that which their optimal combination should be. This combination of weights can form stock portfolios with the best performances that can meet investor preferences. Thus, our methodology can fill the three drawbacks of the classical weighted-scoring approach. [ABSTRACT FROM AUTHOR]

This paper examines the impact of the joints tails of the portfolio return and its empirical volatility on the optimal portfolio choices. We assume that the portfolio return and its volatility dynamic is approximated by a bivariate Markov chain constructed on its historical distribution. This allows the introduction of a non parametric stochastic volatility portfolio model without the explicit use of a GARCH type or other parametric stochastic volatility models. We describe the bi-dimensional tree structure of the Markov chain and discuss alternative portfolio strategies based on the maximization of the Sharpe ratio and of a modified Sharpe ratio that takes into account the behaviour of a market benchmark. Finally, we empirically evaluate the impact of the portfolio and its stochastic volatility joint tails on optimal portfolio choices. In particular, we examine and compare the out of sample wealth obtained optimizing the portfolio performances conditioned on the joint tails of the proposed stochastic volatility model. [ABSTRACT FROM AUTHOR]

The enhanced index tracking problem (EITP) calls for the determination of an optimal portfolio of assets with the bi-objective of maximizing the excess return of the portfolio above a benchmark and minimizing the tracking error. The EITP is capturing a growing attention among academics, both for its practical relevance and for the scientific challenges that its study, as a multi-objective problem, poses. Several optimization models have been proposed in the literature, where the tracking error is measured in terms of standard deviation or in linear form using, for instance, the mean absolute deviation. More recently, reward-risk optimization measures, like the Omega ratio, have been adopted for the EITP. On the other side, shortfall or quantile risk measures have nowadays gained an established popularity in a variety of financial applications. In this paper, we propose a class of bi-criteria optimization models for the EITP, where risk is measured using the weighted multiple conditional value-at-risk (WCVaR). The WCVaR is defined as a weighted combination of multiple CVaR measures, and thus allows a more detailed risk aversion modeling compared to the use of a single CVaR measure. The application of the WCVaR to the EITP is analyzed, both theoretically and empirically. Through extensive computational experiments, the performance of the optimal portfolios selected by means of the proposed optimization models is compared, both in-sample and, more importantly, out-of-sample, to the one of the portfolios obtained using another recent optimization model taken from the literature. [ABSTRACT FROM AUTHOR]

This paper presents how the use of a cleaned and robust covariance matrix estimate can improve significantly the overall performance of maximum variety and minimum variance portfolios. We assume that the asset returns are modelled through a multi-factor model where the error term is a multivariate and correlated elliptical symmetric noise extending the classical Gaussian assumptions. The factors are supposed to be unobservable and we focus on a recent method of model order selection, based on the random matrix theory to identify the most informative subspace and then to obtain a cleaned (or de-noised) covariance matrix estimate to be used in the maximum variety and minimum variance portfolio allocation processes. We apply our methodology on real market data and show the improvements it brings if compared with other techniques especially for non-homogeneous asset returns. [ABSTRACT FROM AUTHOR]

In order to improve upon the performance of a managed portfolio, we propose the use of Marginal Value-at-Risk (MVaR) to ascertain the desirability of assets for inclusion in the managed portfolio, prior to obtaining the optimal managed portfolio. In particular, this is applied on a larger index which comprises of a greater number of assets than a benchmark index and the larger index includes all the assets from the benchmark index. The resulting MVaR index includes exactly the same number of assets as the benchmark index. An empirical study with S&P BSE 100 as the benchmark index, with the MVaR index being derived from S&P BSE 200, with five different optimization problems shows outperformance by the MVaR portfolio over the benchmark portfolio. This highlights the advantage of the inclusion of MVaR resulting in improved performance of the managed portfolio. [ABSTRACT FROM AUTHOR]

We examine, for various educational characteristics of hedge fund managers, the performance profile of hedge fund portfolios along their managers' professional experience path. We find that during the initial years following their graduation, hedge fund managers who majored in business or economics outperform other managers. However, in subsequent years, hedge fund managers who studied science or engineering improve their performance and eventually outperform all other managers. These results are consistent with the view that business education is a substitute for, while science education is a complement to, job experience in acquiring the skills that help hedge fund managers generate excess returns. Compared with cross section studies of the impact of educational variables on productivity, our performance measures are more likely to represent individual productivity, and our estimates are less likely to be biased because of a correlation between educational variables and time-invariant characteristics, such as ability. [ABSTRACT FROM AUTHOR]

Shares choice to enter a portfolio is a good topic in finance and management, as it affects the portfolio performance which is managed by a Fund Manager. In this research, we aim to create an artificial neural network model to choose a share to enter a portfolio based on its financial factors and big data about the financial condition of companies. The artificial neural network model has 15 input nodes of attributes associated with a company's financial situation, 8 hidden layer nodes, and 1 output node. The accuracy of the model is 85.71%, with a learning rate of 0.05 trained over 2000 iterations. [ABSTRACT FROM AUTHOR]

This paper uses a higher moment capital asset pricing model to characterize the returns of several types of hedge fund indices. The quantile regression approach is used to test for any possible changes in the coefficients of the model. The hypothesis that the parameters are stable across the distribution of returns is tested and rejected. The most stable coefficient is the second moment (beta) coefficient. The higher moment coefficients vary considerably. Alpha returns tend to be positive and significant at the center of the distribution. The importance of higher co-moments (i.e., co-skewness and co-kurtosis) is more prevalent at the tails of the distribution of returns suggesting that there are significant tail risks. These findings could potentially have important implications for portfolio strategies and performance evaluation. [ABSTRACT FROM AUTHOR]