Improve Portfolio Performance Research Articles

The influential impacts of international dynamic spillovers in forming investor preferences: a quantile-VAR and GDCC-GARCH perspective

ABSTRACT This study investigates whether representative sectoral stock indices, gold, oil, Bitcoin, and wheat can mitigate risk and improve portfolio performance during normal times versus crises. The cutting-edge Quantile Vector Autoregressive model and the Generalized Dynamic Conditional Correlations (Generalized-DCC) framework are adopted covering from 9 January 2017 until 30 August 2022. Econometric findings by the Q-VAR reveal that oil presents the strongest connection with commodities and stock indices and that Bitcoin and wheat despite their significant linkages with financial markets fail to act as safe havens. Moreover, GDCC-GARCH indicates that the returns of sectoral indices are weakly related but display powerful volatility co-movements. Gold serves efficiently as a hedger and oil follows and both act as better shelters during crises. Nevertheless, Bitcoin partly abides by conventional markets in stressed periods. Notably, wheat reliably works as a hedger overall but does not become a safe haven during crises.

Forecasting ASEAN-5 Stock Index Price Movement Using Machine Learning Techniques

This research investigates the effectiveness of various machine learning models, including Random Forest, Neural Networks, Adaboost, Discriminant Analysis, Logit Model, Support Vectors, and Kernel Factory. The study aims to forecast fluctuations in the ASEAN-5 stock index prices within an eleven-year period. The study provides useful information about how well machine learning techniques can predict changes in the stock market, with potential implications for both academic researchers and market participants. The findings imply that Adaboost consistently outperforms all others in predicting price changes accurately. This shows that machine learning algorithms are capable of accurately forecasting the movement of the ASEAN-5 stock index values. This study contributes to the growing body of research on the use of machine learning techniques in finance and provides investors with information to make informed decisions about investments in the ASEAN-5 region, ultimately leading to increased returns and improved portfolio performance.

Portfolio Selection Redux, or, How the Paradox of Portfolio Efficiency can be used to Improve Portfolio Performance

Portfolio Selection Redux, or, How the Paradox of Portfolio Efficiency can be used to Improve Portfolio Performance

Portfolio optimization based on network centralities: Which centrality is better for asset selection during global crises?

We construct correlation-based networks linking 86 assets (stock indices, bond indices, foreign exchange rates, commodity futures, and cryptocurrencies) and analyze the impact of asset selection on portfolio optimization using different centrality measures (including degree, eigenvector, eccentricity, betweenness, PageRank, and hybrid centralities). In times of a global crisis, peripheral assets located in cross-market networks are more suitable for investment. By comparing portfolio performance based on different centrality measures, we find that (i) hybrid, eigenvector, and PageRank centralities can best improve portfolio performance; (ii) degree centrality is suitable for larger portfolios; and (iii) eccentricity and betweenness centralities are unsuitable for network optimization portfolios. In response, we explain them based on the construction principle of centrality measures. Additionally, our optimal portfolios suggest that investors pay more attention to the role of emerging countries, which are less exposed to external shocks and whose financial markets are more likely to remain stable.

Apple, Microsoft, and Amazon stock price prediction based on ARIMA and LSTM

Along with the advancement in technology and data analysis, efforts have been made to use various factors to predict the stock market to improve portfolio performance and ensure an efficient market. This study explores two stock forecasting models, Long Short-Term Memory(LSTM) and Auto Regressive Integrated Moving Average (ARIMA), and evaluates their performance on the same datasets of historical stock prices of Apple, Microsoft, and Amazon. While ARIMA exhibited superior performance in terms of Root Mean Squared Error(RMSE) and R2 metrics, the research acknowledges inherent limitations, such as the exclusion of potential external influencing factors and the simplistic approach toward LSTM optimization. Despite ARIMA's commendable forecasting ability in this context, the dynamic and non-linear nature of stock prices suggests the potential of hybrid models and broader datasets for future research. The findings underscore the significance of selecting appropriate forecasting tools in the volatile domain of stock investments and pave the way for a more holistic and informed approach to stock price prediction.

Robust portfolio selection with smart return prediction

Return prediction and portfolio decision are closely connected steps in forming optimal portfolios. However, existing studies often separate return prediction from portfolio decisions or overlook the high sensitivity of optimal portfolios to estimated returns, leading to poor out-of-sample performance. To address these two issues simultaneously, this paper proposes a robust portfolio framework that optimizes parameters in return prediction by maximizing robust mean–variance utility. The proposed framework effectively combines return prediction and portfolio decisions while mitigating the uncertainty in return prediction. Empirical analysis on S&P500 constituents demonstrates that, compared to the benchmarks, the proposed framework achieves lower risk and higher risk-adjusted returns, originating from more stable weight estimation and diversified portfolios. Further, we uncover that the market friction characteristics considerably contribute to the proposed strategies’ performance. Our results suggest that integrating return prediction with the robust mean–variance models can significantly improve portfolio performance.

Hedge performance of different asset classes in varying economic conditions

In the realm of long-term investment, strategic portfolio allocation is an essential tool, especially in relation to risk management and return optimisation. There are many ways to pursue optimal portfolio composition, and their effectiveness depends on many factors, including the investor’s goals, risk appetite, and investment horizon. One of the primary means of portfolio optimisation is diversification. The core idea of diversification is to maintain a diverse portfolio with weakly correlated assets that can vastly reduce portfolio exposure to different market stress factors. Diversification is a fundamental strategy in investment and portfolio management that is essential for mitigating risk and enhancing potential returns over the long term. By spreading investments across various asset classes, sectors, geographies, and investment styles, diversification helps reduce the volatility of the overall portfolio. The main subject of this study is the theoretical basis of portfolio diversification and the analysis of historical data to derive optimal strategies for using uncorrelated assets to improve portfolio performance. This paper examines the correlation dynamics between different asset classes, such as stocks, bonds, and alternative investments, and their response to changes in inflation, interest rates, and market volatility, and tests it with historical data to deduce the optimal strategies for using uncorrelated assets to improve portfolio performance. The findings of this study prove the variable relationship between asset classes under specific economic conditions. This study uses historical data to show how different asset classes can be optimally leveraged or adjusted to mitigate risks and capitalise on opportunities presented by shifting economic indicators. This reveals that the hedging benefits of equities, bonds, and gold depend greatly on interest rates, market volatility, and inflation. It also provides guidelines for investors on optimal portfolio allocation and risk management. In conclusion, dynamic portfolio management is an essential tool for reducing the portfolio’s overall volatility while maximising returns. The diversification performance of different financial asset classes depends on major economic indicators such as inflation, interest rates, and market volatility. Investors seeking to optimise their portfolios in anticipation of or in response to economic changes, aiming to maximise returns while controlling for risk, can leverage these results.

Uncertain mean-CVaR model for portfolio selection with transaction cost and investors’ preferences

Portfolio selection is a common practice among investors, scholars often rely on probability statistics to construct portfolios based on the Markowitz mean–variance model. However, due to the complexity of the stock market and the limitations of historical data, it may not be possible to fully predict the future market. In such situations, it is necessary to incorporate expert knowledge and judgments to obtain estimates of security return rates. This paper proposes a class of portfolio models suitable for uncertain environments. We employ the uncertainty theory and Arbitrage Pricing Theory (APT) to measure tail risk and construct a new uncertain mean-Conditional Value-at-Risk (CVaR) model. Additionally, to better match investors’ preferences, this paper takes into account transaction costs and liquidity needs. To solve this problem, we design a hybrid algorithm that incorporates these factors. Finally, we present a numerical experiment to illustrate the performance of the proposed model. In summary, our study offers a novel approach to portfolio selection that considers uncertainty theory, tail risk, and investors’ preferences. The results demonstrate that the proposed uncertain mean-CVaR model with hybrid algorithm optimization can improve portfolio performance in uncertain market conditions.

Optimization of large portfolio allocation for new-energy stocks: Evidence from China

Investment in the fast-growing new-energy of China has gradually attracted great attention. At present, more than 100 new-energy stocks are listed on China’s stock markets. How to effectively manage the investment risk of these stocks and achieve better returns is of great interest to investors and policymakers. In finance, mean–variance portfolio (MVP) is often applied to solve portfolio allocation problems. However, when investing in numerous stocks, the classical MVP is no longer applicable. For large portfolio allocation, this study constructs a comprehensive MVP model, called an unconstrained regression model with latent factors (URELAF). It applies a factor structure with latent factors to modify the covariance matrix estimation in the classical MVP, using an unconstrained penalized regression to estimate the allocation. In addition, to more realistically simulate the investment of stock markets, transaction costs are considered. The empirical results show that URELAF model can control the risk with Sharpe ratio reaching 6 times as many as MVP model, and even improve about 26% compared with the sub-optimal portfolio model. URELAF also outperforms other portfolios with transaction costs. Finally, hypothesis tests further verify that URELAF can significantly improve portfolio performance compared with other portfolio methods for China’s new-energy market.

Attention based dynamic graph neural network for asset pricing

Recent studies suggest that networks among firms (sectors) play a vital role in asset pricing. This paper investigates these implications and develops a novel end-to-end graph neural network model for asset pricing by combining and modifying two state-of-the-art machine learning techniques. First, we apply the graph attention mechanism to learn dynamic network structures of the equity market over time and then use a recurrent convolutional neural network to diffuse and propagate firms' information into the learned networks. This novel approach allows us to model the implications of networks along with the characteristics of the dynamic comovement of asset prices. The results demonstrate the effectiveness of our proposed model in both predicting returns and improving portfolio performance. Our approach demonstrates persistent performance in different sensitivity tests and simulated data. We also show that the dynamic network learned from our proposed model captures major market events over time. Our model is highly effective in recognizing the network structure in the market and predicting equity returns and provides valuable market information to regulators and investors.

Sparse and stable international portfolio optimization and currency risk management

This paper introduces a sparse and stable optimization approach for multi-currency asset allocation, aiming to improve portfolio performance and currency risk management. We demonstrate that the widespread industry practice of employing currency overlay strategies is suboptimal. In contrast, our proposed regularized joint optimization approach, which integrates assets and currencies, consistently outperforms currency overlay strategies as well as equally-weighted and non-regularized global portfolio benchmarks net of transaction costs. On average, the joint optimization approaches achieve 23.3% higher out-of-sample Sharpe ratios compared to their currency overlay counterparts. By addressing parameter uncertainty and inducing sparsity and stability, our method enhances the mean-variance framework, resulting in improved out-of-sample portfolio performance. These findings challenge the prevailing practice of employing currency overlay strategies and highlight the potential for additional gains in risk-adjusted returns through the joint optimization of assets and currencies.

Semiparametric portfolios: Improving portfolio performance by exploiting non-linearities in firm characteristics

Semiparametric portfolios: Improving portfolio performance by exploiting non-linearities in firm characteristics

Robust Portfolio Optimization Strategies in The Serbian Stock Market

Research Question: This paper investigates the performances of six portfolios constructed using robust optimization methods in the Serbian stock market. Motivation: Motivated by the lack of research that analyses the allocation strategies based on robust optimization in the other non-US markets, this paper analyses the ability of these strategies to produce positive performance in the Serbian financial market. Idea: This paper aims to check whether robust strategies can provide positive risk-adjusted performance compared to simple strategies. Data: The analysis was performed on daily data from 2017 to 2020. Tools: We used monthly portfolio rebalancing with an estimation period of 24 months, applying budget and no-short selling constraints in portfolio construction. As a benchmark, we used two simple strategies, the strategy of market index replication and the equal weighting strategy (1/N). Consequently, the performance of the portfolios is evaluated once a month and calculated for the entire investment period. Findings: Empirical results suggest that robust optimization methods improve portfolio performance on a risk-adjusted basis. The increase in performance is affected by an increase in turnover, so the stability of weights in the portfolio depends on the compliance of the model characteristics with the conditions prevailing in the market. Contribution: To the best of our knowledge, this is the first article that analyses the performance of robust optimization portfolios for the Serbian stock markets. Analysing the performance of robust optimization strategies and comparing them to two simple strategies, this paper contributes to the existing literature by checking their possibility of obtaining a positive performance in less developed markets. Additionally, all information presented in this paper could help investors optimize their risk allocation and profitability.

A machine learning based approach to identify key drivers for improving corporate’s esg ratings

Investors increasingly non-financial factors as part of their risk analysis process and growth assessments of corporates. Machine learning (ML) models for predicting ESG scores are an extremely useful tool to help investors make more informed decisions on their portfolios. Such a tool with wide-encompassing alternative data can be useful to the investors. The use of such datasets and machine learning models for ESG ratings can continuously improve the accuracy and reliability of those models. Using machine learning algorithms to identify key drivers of ESG ratings is an effective way of improving portfolio performance. Although the current state of ESG ratings is relatively static, data collection and mapping methodologies are evolving. As more data becomes available, the noise in ESG factors will become less important. This unique document provides a machine learning algorithm for predicting an ESG rating based on a company's financial and non-financial attributes. The financial and non-financial attributes of corporations are extracted from Moody's Orbis and Ratings from S&P. The objective here is to predict the ESG rating of companies where the ESG rating is not easily accessible. At the same time, this approach would allow investors to have a suitable framework for investments based on ESG ratings. With the latest financial and non-financial disclosure by a corporate an ESG score can be predicted which can be used to identify its riskiness with a corresponding increase/decrease of ESG score.

Dynamic Covariance Matrix Estimation and Portfolio Analysis with High-Frequency Data

Abstract The covariance matrix associated with multiple financial returns plays foundational roles in many empirical applications, for example, quantifying risks and managing investment portfolios. Such covariance matrices are well known to be dynamic, that is, their structures change with the underlying market conditions. To incorporate such dynamics in a setting with high-frequency noisy data contaminated by measurement errors, we propose a new approach for estimating the covariances of a high-dimensional return series. By utilizing an appropriate localization, our approach is designed upon exploiting generic variables that are informative in accounting for the dynamic changes. We then investigate the properties and performance of the high-dimensional minimal-variance sparse portfolio constructed from employing the proposed dynamic covariance estimator. Our theory establishes the validity of the proposed covariance estimation methods in handling high-dimensional, high-frequency noisy data. The promising applications of our methods are demonstrated by extensive simulations and empirical studies showing the satisfactory accuracy of the covariance estimation and the substantially improved portfolio performance.

Moderating Effect of Tactical Asset Allocation on the Risk-Return Relationship in the Nigerian Stock Market

Before making investment decisions, the investor must find out the risk-return characteristics of investments with the help of investment strategies. These investment strategies, including drawdown, tactical asset allocation and short selling, are used by investors and fund managers to improve portfolio performance by maximizing returns and minimizing risks. This study aims to examine the moderating effect of tactical asset allocation on the risk-return relationship in the Nigerian stock market. The study sample is 90 stocks that are consistently traded in the Nigerian stock market within the period of sixteen years on a monthly basis. The study employed time series data which were extracted from the NGX website, annual financial statement, and CBN statistical bulletin. This study's data collection and analysis framework was based on the methodology of Fama and French (2015) using FamaMacbeth's two-step regression. The study used the difference between the logarithmic present value of the price and the previous value of the price to compute the return. Evidence from the result revealed that tactical asset allocation is not significantly priced under the CoFF5F and HMFF5F in the Nigerian stock market. Also, introducing tactical asset allocation as the moderating variable does not improve the relationship between risk and return in the Nigerian stock market. In light of this, the study concluded that tactical asset allocation could not be used to improve the relationship between risk and return through the minimization of risk and maximization of return in the Nigerian stock market. The study recommends that other investment strategies, such as drawdown, short selling etc., can be used by investors to improve the relationship between risk and return in the Nigerian stock market.

Dynamic Interactions Between the Bitcoin Price Index and Widely Traded Financial Assets: Evidence from the Recent COVID-19 Crisis

We investigate the connectedness between the Bitcoin Price Index (BPI) and widely traded financial assets from different markets (equities, bonds, commodities and fiat currency). Using daily data from 5 August 2013 to 31 August 2021 (before and during the COVID-19 crisis), we run the VAR model estimation to investigate any connectedness between the BPI and financial assets, followed by the Granger causality test. We then test Diebold and Yilmaz’s (2012) framework to analyse the spill-over effects among our set of variables. Our empirical results provide strong evidence that the BPI index exhibits significant independence from widely traded financial assets. This independence is less pronounced during the COVID-19 crisis, but remains relatively important. To test whether Bitcoin constitutes a relevant diversification vehicle, we compute the Sharpe portfolio performance index of two portfolios of conventional assets with and without the BPI, before and during the COVID-19 crisis. Our results show that the introduction of the BPI index as a diversification asset does not improve portfolio performance. Overall, our empirical findings are robust to different robustness tests and provide several implications for hedgers, portfolio managers and policymakers.

Portfolio Selection Based on EMD Denoising with Correlation Coefficient Test Criterion.

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.

Dynamic interactions between the bitcoin price index and widely traded financial assets: evidence from the recent covid-19 crisis

We investigate the connectedness between the Bitcoin Price Index (BPI) and widelytraded financial assets from a variety of markets (equities, bonds, commoditiesand fiat currency). Using daily data from 5 August 2013 to 31 August 2021 (beforeand during the COVID-19 crisis), we run the VAR model estimation to investigateany connectedness between the BPI and financial assets, followed by the Grangercausality test. We then test Diebold and Yilmaz’s (2012) framework to analyse thespillover effects among our set of variables. Our empirical results provide strongevidence that the BPI index exhibits significant independence from widely tradedfinancial assets. This independence is less pronounced during the COVID-19 crisis,but remains relatively important. To test whether Bitcoin constitutes a relevantdiversification vehicle, we compute the Sharpe portfolio performance index of twoportfolios of conventional assets with and without the BPI, before and during theCOVID-19 crisis. Our results show that the introduction of the BPI index as a diversificationasset does not improve portfolio performance. Overall, our empiricalfindings are robust to different robustness tests and provide several implicationsfor hedgers, portfolio managers and policymakers.

The predictive ability of stock market factors

PurposeThis paper aims to ask whether a range of stock market factors contain information that is useful to investors by generating a trading rule based on one-step-ahead forecasts from rolling and recursive regressions.Design/methodology/approachUsing USA data across 3,256 firms, the authors estimate stock returns on a range of factors using both fixed-effects panel and individual regressions. The authors use rolling and recursive approaches to generate time-varying coefficients. Subsequently, the authors generate one-step-ahead forecasts for expected returns, simulate a trading strategy and compare its performance with realised returns.FindingsResults from the panel and individual firm regressions show that an extended Fama-French five-factor model that includes momentum, reversal and quality factors outperform other models. Moreover, rolling based regressions outperform recursive ones in forecasting returns.Research limitations/implicationsThe results support notable time-variation in the coefficients on each factor, whilst suggesting that more distant observations, inherent in recursive regressions, do not improve predictive power over more recent observations. Results support the ability of market factors to improve forecast performance over a buy-and-hold strategy.Practical implicationsThe results presented here will be of interest to both academics in understanding the dynamics of expected stock returns and investors who seek to improve portfolio performance through highlighting which factors determine stock return movement.Originality/valueThe authors investigate the ability of risk factors to provide accurate forecasts and thus have economic value to investors. The authors conducted a series of moving and expanding window regressions to trace the dynamic movements of the stock returns average response to explanatory factors. The authors use the time-varying parameters to generate one-step-ahead forecasts of expected returns and simulate a trading strategy.