Portfolio Performance Research Articles

Expert aggregation for financial forecasting

Machine learning algorithms dedicated to financial time series forecasting have gained a lot of interest. But choosing between several algorithms can be challenging, as their estimation accuracy may be unstable over time. Online aggregation of experts combine the forecasts of a finite set of models in a single approach without making any assumption about the models. In this paper, a Bernstein Online Aggregation (BOA) procedure is applied to the construction of long-short strategies built from individual stock return forecasts coming from different machine learning models. The online mixture of experts leads to attractive portfolio performances even in non-stationary environments. The inclusion of neural networks experts in the aggregation contributes to a better average return, while Ordinary Least Squares with Huber Loss experts contribute to lower risk. The aggregation outperforms individual algorithms, offering a higher portfolio Sharpe ratio, lower shortfall, with a similar turnover. Extensions to expert and aggregation specialisations are also proposed to improve the overall mixture on a family of portfolio evaluation metrics.

Dynamic core-satellite investing using higher order moments: an explicit solution

The goal of core-satellite investing is to optimally balance the portfolio allocation between a core and satellite investment. This paper provides an explicit solution when the investor's optimality criterion is the third-order and fourth-order expansion of the expected utility function, respectively. Based on a numeric example, we document the sensitivity of the proposed weights to coskewness and cokurtosis components. Finally, we use ETFs to examine the portfolio performance of the core-satellite strategy with higher order moments. We document that integrating the higher order moment in core-satellite investing can improve the financial performance of a portfolio.

Extended finite similitude and dimensional analysis for scaling

The theory of scaling called finite similitude does not involve dimensional analysis and is founded on a transport-equation approach that is applicable to all of classical physics. It features a countable infinite number of similitude rules and has recently been extended to other types of governing equations (e.g., differential, variational) by the introduction of a scaling space Omega _{beta }, within which all physical quantities are deemed dependent on a single dimensional parameter beta . The theory is presently limited to physical applications but the focus of this paper is its extension to other quantitative-based theories such as finance. This is achieved by connecting it to an extended form of dimensional analysis, where changes in any quantity can be associated with curves projected onto a dimensional Lie group. It is shown in the paper how differential similitude identities arising out of the finite similitude theory are universal in the sense they can be formed and applied to any quantitative-based theory. In order to illustrate its applicability outside physics the Black-Scholes equation for option valuation in finance is considered since this equation is recognised to be similar in form to an equation from thermal physics. It is demonstrated that the theory of finite similitude can be applied to the Black-Scholes equation and more widely can be used to assess observed size effects in portfolio performance.

Optimal Portfolio Choice with Unknown Benchmark Efficiency

When a benchmark model is inefficient, including test assets in addition to the benchmark portfolios can improve the performance of the optimal portfolio. In reality, the efficiency of a benchmark model relative to the test assets is ex ante unknown; moreover, the optimal portfolio is constructed based on estimated parameters. Therefore, whether and how to include the test assets becomes a critical question faced by real world investors. For such a setting, we propose a combining portfolio strategy, optimally balancing the value of including test assets and the effect of estimation errors. The proposed combining strategy can work together with some existing estimation risk reduction strategies. In both empirical data sets and simulations, we show that our proposed combining strategy performs well. This paper was accepted by Agostino Capponi, finance. Supplemental Material: The data files and online appendix are available at https://doi.org/10.1287/mnsc.2021.01767 .

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.

Analysis of Stock Portfolio Performance Using Passive Strategy and Active Strategy with Single Index Model

This study aims to determine and analyze the differences in return and risk performance results of passive and active strategies using the Single Index Model. Then measure the return performance using the Sharpe Index, Treynor, and Jensen's Alpha. This research was conducted on Sri-Kehati index stocks for the period November 2019 to November 2021. Based on passive portfolio strategy research, there are three stocks that form the optimal portfolio, namely BBCA, BBRI, SIDO. While based on active portfolio strategy research, in the first year there were three stocks that formed the optimal portfolio, then in the second year there were seven stocks forming the optimal portfolio, namely BBCA, BBRI, DSNG, INCO, SIDO, SMGR, WIKA. Based on performance measurement using Sharpe, Treynor and Jensen's Alpha indices, the Active Portfolio Strategy is better than the Passive Portfolio Strategy. Meanwhile, based on the difference test using the Mann Whitney U test method, it can be concluded that there is no significant difference in return performance between passive and active portfolio strategies.

Enhancing portfolio resilience during crisis periods: Lessons from BRICS indices and multi asset strategies

This paper uses Markowitz’s mean-variance model to construct an investment portfolio incorporating multiple assets – BRICS equity indices, Gold, crude oil, bonds, and cryptocurrencies. The optimally created risky portfolios outperform alternative portfolio optimization methods – the naive portfolio and the equal risk contribution portfolio; and established indices – the S&P 500 and the MSCI Emerging Equity Index in terms of metrics – adjusted Sharpe ratio, modified Sharpe ratio, and the modified Value at Risk. The findings are validated across different periods, including the COVID-19 period and the Russian invasion of Ukraine, including various in and out of sample periods. The findings highlight the benefits of portfolio diversity, mainly using BRICS indices, Gold, and Brent Crude oil, and challenge the notion of limited diversification benefits in BRICS indices found in previous studies. This paper further suggests the potential of emerging market bonds ETF as a diversification option during turbulent economic periods and highlights the limitations of cryptocurrencies in optimizing multi asset portfolios. By adopting the recommended multi asset portfolios, investors can enhance their risk-return trade-offs and achieve superior performance compared to the S&P500 and MSCI emerging indices. Lastly, the paper recommends future research opportunities in measuring portfolio performance and hedging strategies considering risk-adjusted return measurements, transaction expenses, and dynamic rebalancing techniques.

Exclude with Impunity: Personalized Indexing and Stock Restrictions

Using simulated historical backtests, we study the impact of stock exclusions on the performance of passive and active portfolios. We find that at low to moderate numbers, stock exclusions have very little influence on passive portfolios. Their effects on active portfolios vary by the factor in consideration and the portfolio construction method, but the magnitudes are much smaller than suggested by the percentage of stocks being excluded. We find similar patterns with industry-concentrated exclusions. Overall, our results suggest that investors should feel comfortable excluding a fairly large number of stocks before experiencing any significant deterioration in their investment performance.

The commodity risk premium and neural networks

The paper uses linear and nonlinear predictive models to study the linkage between a set of 128 macroeconomic and financial predictors and the risk premium of commodity futures contracts. The linear models use shrinkage methods based on either naive averaging or principal components. The nonlinear models use feedforward deep neural networks (DNN) either as stand-alone or in conjunction with a long short-term memory network (LSTM). Out of the four specifications considered, the LSTM-DNN architecture best captures the risk premium, which underscores the need to estimate models that are both nonlinear and recurrent. The superior performance of the LSTM-DNN portfolio persists after accounting for transaction costs or illiquidity and is unrelated to previously-documented commodity risk factors.

Does commodity exposure benefit traditional portfolios? Evidence from India

Commodities and commodity futures are expected to benefit stock and bond portfolio diversification because traditional asset types like equities and bonds have low correlations with commodities. During periods when stocks and bonds may underperform, commodities may provide a hedge against inflation and other economic uncertainties. This study investigates the diversification benefits of adding commodities to a traditional portfolio of stock and bonds from the perspective of an Indian investor. It employs several commonly used asset allocation strategies such as mean-variance, equal risk contribution, most diversified portfolio, and equal weight portfolio on different commodity derivative groups. The performance of various portfolios indicates that not all commodity groups provide substantial diversification benefits to a traditional portfolio. Agricultural commodities enhance performance (with an Omega ratio of 1.654), whereas metal and energy-related commodities do not diversify the traditional portfolio significantly (Omega ratio of 1.087 and 0.945, respectively). Gold and different equity sectors also provide some diversification benefits. This study also supports the hypothesis that the behavior of different commodity groups is quite different. AcknowledgmentThe infrastructural support provided by the FORE School of Management, New Delhi, in completing this paper is gratefully acknowledged.

Socially responsible portfolios,environmental, social, corporate governance (ESG)efficient frontiers, and psychic dividends

AbstractThe aim of this article is to evaluate the performance of investment portfolios built under environmental, social, and corporate governance (ESG) criteria or socially responsible portfolios, based on companies listed on three representative stock exchanges in Latin America (Chile, Colombia, and Peru) for the period 2011–2019. The performance of portfolios comprising high‐ESG stocks was compared with that of low‐ESG performance portfolios and with portfolios of companies that did not report such information, as well as against the main index of each market. A novel utility function was defined that allows evaluating different degrees of propensity to responsible investment, based on which restricted optimization processes were conducted to build efficient frontiers that combine traditional mean–variance aspects with ESG elements. Based on these frontiers, a measure of the psychic dividend or ESG utility premium generated by investing in high‐ESG portfolios is proposed. Results obtained in risk and return rates and Jensen, Treynor, alpha, VaR, tracking error, information coefficient, efficient frontiers, and utility premium show the value of following responsible investment criteria and the clear disadvantages in investing in companies that do not report ESG information. This research contributes to the debate on the importance of socially responsible investment guided by ESG criteria, filling a gap in the literature regarding Latin America and confirming the better performance by calculating a wide range of portfolio evaluation indicators. We proposed a novel approach to optimization with sustainability constraints, incorporating the utility premium derived from investing in stocks with better ESG performance.

COMPARATIVE ANALYSIS OF SHARIA AND CONVENTIONAL STOCKS PORTFOLIO PERFORMANCE USING SHARPE, TREYNOR AND JANSEN METHODS

The Sharia capital market emerged as an alternative vehicle for the investor community to invest in the financial world in accordance with Sharia principles. As an alternative investment vehicle, the Sharia capital market is of course also targeted by investors who care about Sharia in addition to the general objective as a vehicle used to a profitable investing. Based on this basic framework, this research was conducted with the aim of analyzing and comparing stock performance in the form of stock portfolios between Sharia-based and conventional one. The JII70 stock index was used as an object for the Sharia stock portfolio, while the conventional stock portfolio was represented by the LQ45 index. The performance assessment used on these two portfolios was a portfolio performance assessment using the Sharpe, Treynor, and Jensen methods during the Covid-19 pandemic. The performance of these stock portfolios according to the three methods showed positive results. The performance of the JII70 stock portfolio was lower than the LQ45 index although it is insignificant. Meanwhile, according to the Treynor index, the performance of the JII70 was better than the LQ45 although it is insignificant.

The Dollar Cost Averaging, Lump Sum, and Value Averaging Strategies in Mutual Fund Investments

Investment strategy and portfolio management are crucial considerations when investing in mutual funds. This research aims to analyze the effectiveness of achieving optimal returns by simulating dollar cost averaging, lump sum, and value averaging approaches. This analysis is conducted about the performance of a mutual fund portfolio, utilizing the Sharpe and Treynor methods. The research sample employs a purposive sampling technique, selecting the top 5 mutual funds in terms of performance, managed by different investment managers in the year 2022. Simulations are being conducted over three specific periods. In addition to mutual funds, a comparative analysis was conducted involving the Jakarta Composite Index (JCI) and 10-year government bond yields (SUN). The simulation results on equity funds for the three periods indicate that the Lump Sum investment method outperforms dollar cost averaging and value averaging, particularly over 6 years. This finding is further corroborated by the Kruskal-Wallis test, which highlights a significant variance in return performance. The results of the Sharpe and Treynor investment methods exhibit significant differences, as confirmed by the Mann-Whitney test. Lastly, regarding benchmark comparisons, the performance of equity funds surpasses that of the benchmark.

Dynamic connectedness, spillover, and optimal hedging strategy among FinTech, Sukuk, and Islamic equity markets

The paper investigates the dynamic connectedness, spillover, and optimal hedging strategy of the FinTech, Sukuk, and Islamic equity markets. The CAViaR approach, TVP-VAR Frequency connectedness, and network connectedness approaches are used. We also apply the MVP, MCP, and MCoP approaches to construct portfolios based on the Fintech, Sukuk, and Islamic equity indices. We then compute hedge effectiveness, portfolio performance, and Sharpe ratios. We find that FinTech markets are predominantly intra-connected in the short and medium term; they are significantly interconnected in the long term. In terms of frequency decomposition, volatility transmission among the variables dominates in the short term in comparison with other examined durations. The Russian-Ukrainian War and COVID-19 pandemic both saw a considerable increase in the intensity of volatility transmission. There is higher information transmission from Islamic equity indices and less effective information transmission from Sukuk and Fintech indices. Our findings suggest that the dynamic portfolio weights for MCP and MCoP seem to be similar, but clearly differs from MVP approach. When delving into the existence of Fintech indices as a part of an international fixed-income Islamic investor's portfolio, our paper's findings – being robust to the portfolio construction method – establish that Fintech indices do have a notable role in fixed-income Islamic investment portfolios. Finally, we conclude by highlighting the fact that the benefits of diversifying a portfolio with FinTech and Islamic assets fluctuate with time and on a regular basis.

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.

Effect of Corporate Social Responsibility on Portfolio Performance: Evidence From Turkey

This study investigates the performance of corporate social responsibility (CSR) portfolios based on ESG scores of stocks traded in Borsa Istanbul (BIST). It also evaluates the performance of a trading strategy that represents buying portfolios that include companies with high CSR performance and selling portfolios comprising companies with low CSR performance. Therefore, two portfolios with high and low CSR performance were formed from stocks traded in Borsa Istanbul. These portfolios’ performances were compared from July 2010 to June 2020. The findings show that the alpha coefficient of the portfolio containing stocks of companies with high CSR performance is generally positive and significant. Thus, companies’ past CSR performances provide valuable information for investors. Additionally, based on this, investors can achieve a superior performance against the market. However, the alpha of the difference portfolio, which shows the difference between the two portfolios’ performance, is, in most cases, insignificant. This suggests that there is no proof that the portfolio comprising companies with high CSR performance is superior to the portfolio including companies with low CSR performance. These findings are supported by additional testing. Consequently, our result provides supporting evidence for the “no effect” hypothesis.

Russia‐Ukraine war and G7 debt markets: Evidence from public sentiment towards economic sanctions during the conflict

AbstractWar‐related expectations cause changes to investors' risks and returns preferences. In this study, we examine the implications of war and sanctions sentiment for the G7 countries' debt markets during the Russia‐Ukraine war. We use behavioural indicators across social media, news media, and internet attention to reflect the public sentiment from 1st January 2022 to 20th April 2023. We apply the quantile‐on‐quantile regression (QQR) and rolling window wavelet correlation (RWWC) methods. The quantile‐on‐quantile regression results show heterogenous impact on fixed income securities. Specifically, extreme public sentiment has a negative impact on G7 fixed income securities return. The wavelets correlation result shows dynamic correlation pattern among public sentiment and fixed income securities. There is a negative relationship between public sentiment and G7 fixed income securities. The correlation is time‐varying and highly event dependent. Our additional analysis using corporate bond data indicates the robustness of our findings. Furthermore, the contagion analysis shows public sentiment significantly influence G7 fixed income securities spillover. Our findings can be of great significance while framing strategies for asset allocation, portfolio performance and risk hedging.

The overlooked momentum traders in 401(k) plans

Using a unique dataset on over one million 401(k) traders, we investigate momentum trading in 401(k) plans. We identify momentum traders in each quarter and evaluate how these traders perform. Results indicate the existence of momentum traders. However, there is no evidence that they successfully improve their portfolio performance. Instead, momentum sellers sell the outperformed funds. Overall, momentum traders could lose up to 2.14% per year. In seeking to explain such losses, we observe that 401(k) momentum traders follow a naïve momentum strategy. They do not have the ability to select funds with momentum investing styles but, instead, simply chase past returns.

Cryptocurrency Portfolio Rebalancing: A Comparative Analysis of Time-Based and Threshold-Based Rebalancing Strategies

The rise of cryptocurrencies as an asset class has attracted the attention of investors and portfolio managers alike (Baur & Hendershott, 2018; Chuen, Guo, & Wang, 2017). One of the key challenges in managing a cryptocurrency portfolio is the high volatility and uncertainty of the market. To address these challenges, rebalancing, which involves adjusting the weights of assets in a portfolio to align with a predetermined asset allocation, is applied to maintain a diversified portfolio and manage the risks of digital assets (Bakry, Rashid, Al-Mohamad, & El-Kanj, 2021). For any traditional assets, a rebalancing strategy is widely recognized as a technique to mitigate the impact of market volatility and improve the risk-return trade-off of the portfolio (Gervais, Koutmos, & Udell, 2015; Tsai, 2001). It is considered an effective method of achieving returns maximization and risk minimization objectives as it helps reduce the impact of market volatility and keep the portfolio aligned with the investor's risk tolerance and investment goals. However, there is still limited empirical research on its impact on cryptocurrency portfolio performance. Given this gap in the literature, the study aims to shed useful light on the effects of different rebalancing strategies on cryptocurrency portfolio management. Keywords: Cryptocurrency, Mean-Variance Optimization, Portfolio Management, Rebalancing Strategies, Risk-Adjusted Returns