Portfolio Management Strategies Research Articles

Stock Prediction using Deep Learning: A Comparison

Stock market prediction (SMP) is one of the most important areas in finance that greatly helps investors and financial institutions to anticipate market fluctuations and make wise decisions. This becomes very important in view of the potential challenge of obtaining optimum revenues and effective portfolio management strategies in view of the volatile market environments typically governed by underlying economic and socio-political influences. This paper proceeds to categorize stock prediction works into three principal categories: Convolutional Neural Network (CNN)-based models, Recurrent Neural Network (RNN)-based models, and hybrid models using more than one forecasting technique. We reviewed nine research papers and compared them in view of different datasets to show efficacy distinctions among these methodologies. Our experiments stated that the hybrid models that marry the spatial data processing ability of CNNs to the temporal sensitivity of RNNs outperform other approaches in accuracy and strength of predictions. This synthesis approach captures complex patterns more efficiently as well as relevant to the dynamic nature of financial markets. Results underscore the potential contribution of hybrid frameworks being a leading methodology for future developments in SMP. Further improving these models with the advancements of machine learning and data analytics may likely push the boundaries of what is feasible in financial forecasting.

Price Bubble and Co-bubble in the Green Economy Market

In light of growing concerns about climate change and environmental issues, investor interest has surged in the new green economy market. However, the existing literature is limited regarding potential price bubble and co-bubble within this new domain. This study examines price bubble and co-bubble in the new green economy market, covering 31 indexes classified into three groups: the green economy market and its components, geographical regions, and sectors. Using daily data from August 31, 2005, to May 31, 2024, a test procedure is first applied to detect periods of price bubble in the various indexes, then logistic regressions are employed to examine price co-bubble behaviours. The results show evidence of price bubble in the green economy market, particularly in solar and wind indexes, with peaks during the COVID-19 pandemic and Russia-Ukraine conflict, whereas the water index is the least prone to price bubble. Regarding geographical region, the USA market exhibits a higher tendency for price bubble than the Asian or European markets. Several sectors are resistant to price bubble. The co-bubble analysis reveals a strong reliance of wind index on price bubble in the solar and water indexes. Price bubble in Asia significantly influences price bubble in Europe and the USA. These findings have implications for investment portfolio management and risk management strategies in the new green economy market.

DEFINING COMPONENTS OF THE METHODOLOGICAL PLATFORM FOR FORMING A BUSINESS PORTFOLIO OF A COMPANY IN THE UPDATED FORMAT OF MODERN DEVELOPMENT

The article is devoted to the analysis of the economic and operational imperatives of forming a business portfolio for a development company in the construction sector. A successful business portfolio management strategy requires the integration of financial, organizational, and technological aspects to ensure the sustainability and competitiveness of the business. In modern conditions, real estate development is one of the key factors that determines the dynamics of enterprise development, as it includes a comprehensive approach to asset management, from planning and financing to the construction and operation of objects. The theoretical and methodological foundations of the genesis of development at the current stage of the construction market's evolution have been analyzed.The methodological platform for forming a business portfolio should be based on the principles of rational resource management, risk analysis, and technological optimization. Changes in development activities require the active use of digital tools and a comprehensive approach to managing residential, commercial, and industrial properties, which allows for the maximization of profitability and minimization of risks.The article discusses the main stages of portfolio formation, such as strategic planning, selection of investment objects, and their integration into the overall structure of the enterprise. An economic and mathematical formalization of the process is also provided. For the successful operation of a development company, it is crucial to ensure coordinated work at all stages of the project — from planning and financing to construction and commissioning of the facilities.Particular attention is paid to the methods of economic and mathematical modelling (EMM) and quantitative risk analysis, which have become the basis for the development of the latest asset management strategies. The study analyses 35 different techniques. Each methodology offers unique tools for the effective management of development projects that allow forecasting financial flows, determining optimal investment strategies, and building the best plans for the development of a real estate portfolio. The specific methods used to value residential, commercial and industrial real estate are also discussed, taking into account their different levels of risk and return.It is important to note that the updated methodological platform is suitable for adaptation to the latest technologies and digital tools. This includes the introduction of a project management system, the use of artificial intelligence technologies to analyse large amounts of data, and the use of analytical tools to predict market trends. This approach helps to optimise asset management in a changing market environment. The analysis of the main components of the business portfolio formation platform also showed that important factors for the successful implementation of development projects are the speed of response to market changes, flexibility of management decisions, and the ability to minimise risks at all stages of the project.

Quantitative Portfolio Management: Review and Outlook

This survey aims to provide insightful and objective perspectives on the research history of quantitative portfolio management strategies with suggestions for the future of research. The relevant literature can be clustered into four broad themes: portfolio optimization, risk-parity, style integration, and machine learning. Portfolio optimization attempts to find the optimal trade-off of future returns per unit of risk. Risk-parity attempts to match the exposure of various asset classes such that no single asset class dominates portfolio risk. Style integration combines risk factors on a security level such that rebalancing differences cancel out. Finally, machine learning utilizes large arrays of tunable parameters to predict future asset behavior and solve non-convex optimization problems. We conclude that machine learning will likely be the focus of future research.

Impact of ESG Risk on Portfolio Optimization and Returns: An Analysis Using the Markowitz Model

This paper explores the integration of Environmental, Social, and Governance (ESG) factors into portfolio optimization using the Markowitz Model, focusing on two groups of ten stocks each from the Technology, Media, and Telecom (TMT) sectors. These stocks are categorized into low and high ESG risk groups according to established ESG rating agencies. Employing historical data, the study computes key financial metrics such as annualized returns, standard deviation, and Sharpe ratios to conduct various portfolio optimizations including the minimal risk frontier, efficient frontier, and inefficient frontier, while also applying five specific operational constraints reflective of real-world investment limits. The analysis distinctly highlights the superior performance of the low ESG risk group, which demonstrated higher returns and better risk-adjusted return profiles, as evidenced by elevated Sharpe ratios. These findings suggest that ESG integration not only aligns with broader societal goals but also enhances financial performance, especially under diverse regulatory and strategic constraints. This research enriches the discourse on sustainable investing by providing empirical evidence on how ESG factors influence traditional portfolio management strategies, potentially guiding future investor decisions and promoting a shift towards more sustainable investment practices.

Strategic portfolio rebalancing: Integrating predictive models and adaptive optimization objectives in a dynamic market

Adjusting investment strategy is one of the ways to handle dynamic market conditions. This study proposes a novel portfolio management strategy using appropriate optimization objectives for different stock market trends while also incorporating market trends and stock return predictions The optimization objectives that will be evaluated for different market trends are maximizing the Sharpe ratio, minimizing risk, and minimizing expected shortfall. This study utilizes simulation modelling with various predictive models on building the portfolios. The results show that, in an upward market trend, the strategy is to choose stocks with positive returns, and the objective is to maximize the Sharpe ratio. The portfolio that follows this strategy during upward market trends has greater returns than both the Indonesian Composite Index and LQ45, which serve as stock market benchmarks, with 90% certainty. Meanwhile, during the downward market trend, the strategy is to choose stocks with a negative correlation with the Indonesian Composite Index, and the proper optimization objective is to minimize risk. A portfolio that follows this strategy during downward market trends has greater returns than stock market benchmarks with 95% certainty. Across the evaluation period from 2018 to 2023, the portfolio using the proposed strategy outperforms both stock market benchmarks, with a higher quarterly Sharpe ratio of 0.3047 and cumulative return of 107.90%. The proposed portfolio has a higher quarterly return than the stock market benchmark with 99% certainty. Therefore, the proposed strategy shows a promising result in a dynamic market.

Analyzing downside risk of BRICS stock indices: insights from value at risk and time series econometrics

Purpose This paper aims to analyze the downside risk for the stock indices of BRICS countries. The study also aimed to study the interrelationship, directional influence and interdependence among the stock exchanges of BRICS economies to provide insights for policymakers, fund managers, investors and other stakeholders. Design/methodology/approach The authors used Value at Risk (VaR) as an indicator of downside risk and time series econometrics for measuring the long run relationship, directional influence and interdependence. Findings The calculated VaR estimates, long-run linkages and strong interdependence among these indices especially with the returns of Brazil exerting a notable impact on the returns of other BRICS nations. These results emphasize the significance of taking into account cross-country spillover effects and domestic market dynamics in the context of portfolio management and risk assessment strategies. Further, from the extended results of variance decomposition analysis, the authors find that Brazil’s, China’s and South African stock market returns have a significantly lagged impact on their own stock market, while Russia’s and India stock market returns do not have a significantly lagged impact on their own stock markets. Originality/value To the best of the authors’ knowledge, this is the first study comprehensively analyzing the BRICS indices downside risk through the historical simulation method of VaR estimation, which is an unexplored area of risk management.

Application of Financial Mathematical Models Combined with Root Algorithms in Finance

Investors in the financial markets must deal with various hazards, for which they must create prudent investment portfolios and risk management plans. A multi-objective optimisation approach is proposed using the root algorithm to create a multi-objective root system growth model based on many clusters. An investment risk management optimisation model based on root system growth is built into the study using distributed decision-making. To create a multi-objective root algorithm-based portfolio optimisation model, the Markowitz mean-variance model and a multi-objective root algorithm are employed. Accordingto the findings, the multi-group multi-objective root system method has a real Pareto frontier solution that is more accessible, has a faster convergence rate, and has lower fitness values. The root algorithm’s solutions are workable, and the final risk values of 0.0105, 0.0082, and 0.4623 for the 2, 4, and 6 investment objectives are all in the low-risk class range. The optimal set of solutions discovered by the algorithm had better distributivity and convergence. The Hypervolume values for the multi-group multi-objective root algorithm were 5.5298 and 3.9628 for the dual-objective portfolio and the tri-objective portfolio of investment return costs, respectively. The findings of this study can guide the development of portfolio and risk management strategies.

Asymmetric connectedness and investment strategies between commodities and Islamic banks: Evidence from gulf cooperative council (GCC) markets

The study uses the data of thirteen Islamic Banks (IB) in the GCC region and sixteen commodities that include soft agriculture, energy, industry, and precious metal commodities. Murabaha transactions makes up most of the revenues of the Islamic banks, whereas commodities set up the biggest portion of the assets among Murabaha transactions, therefore commodities and IB revenues are expected to comove. Interestingly, empirical findings suggest that most of the Islamic banks and commodities are not significantly affected by the shocks from other markets. We further observe that negative shocks have a higher impact on market connectedness among used assets compared to the positive returns and find a significant role of risk variables in explaining the magnitude of spillover between used assets. We perform robustness of our results in sub-samples periods during Shale Oil Revolution, Global Financial Crisis, and the COVID-19. Additionally, the multivariate portfolio analysis shows some risk reduction properties of the majority of the used assets. The performance evaluation measures demonstrate that weights selected based on dynamic connectedness network presents diversification opportunities. These findings help investors and portfolio managers to remain alert to the movements of the risk factors and calibrate there hedging and portfolio management strategies by taking long and short positions as incorporation of Islamic banks and commodities in the GCC region in a portfolio could yield risk reduction benefits and profitability.

VIX-managed portfolios

We propose a simple portfolio management strategy that gauges the leverage based on the observed implied volatility index (VIX). The strategy involves taking less risk when the cumulative previous-month VIX is high and more when it is low. We show that the strategy yields more stable weights and thus requires less rebalancing than comparable strategies based on realized volatility. As a result, it produces substantially higher spanning regression alphas when transaction costs are taken into account. We document this for ten equity factors, six classes of mean–variance efficient portfolios and 176 anomaly portfolios. We argue that the superior performance of the VIX-based strategy is driven by its ability to time volatility and tail risk simultaneously, resulting from the forward-looking nature of the information entailed in the index and the higher-order return moments embedded in the implied volatility smile.

Does asset-based uncertainty drive asymmetric return connectedness across regional ESG markets?

This paper investigates the impact of asset-based uncertainty on the asymmetric return connectedness and hedging effectiveness of regional environmental, social and governance (ESG) equity markets from January 2017 to December 2022. The results of the asymmetric time-varying parameter vector autoregressive connectedness approach show strong dynamic connectedness within regional ESG markets, with the dominance of negative returns intensifying during COVID-19. Quantile regressions reveal that uncertainty in crude oil and bond markets negatively affects asymmetric return connectedness across bearish, normal and bullish market periods, whereas uncertainty in stock, gold and exchange rate markets has a positive impact. Overall, asset-based uncertainty influences negative return connectedness more than positive return connectedness, and a varied influence of asset-based uncertainty is noted during COVID-19 and the Russia–Ukraine war. A portfolio analysis shows that all ESG markets significantly contribute to higher hedging effectiveness, with a portfolio constructed based on the minimum connectedness approach outperforming the other portfolios. The findings provide policy implications for portfolio and risk management strategies.

Examining the quantile cross-coherence between fossil energy and clean energy: Is the dependence structure changing with the COVID-19 outbreak?

The advent of COVID-19 has markedly affected financial and energy markets. Clean energy positions itself as a feasible substitute for fossil fuels, and the crisis has altered the interdependence of these two counterpart markets. This study uses quantile cross-spectral analysis to investigate the dependence structure features of the fossil and clean energy markets, pre- and post-COVID-19 outbreak, under various market conditions and across different investment horizons. Empirical results suggest an anomalous intensification or inversion in the interaction between fossil and clean energy under extreme market conditions post-COVID-19 outbreak, manifesting either an extraordinarily high or low dependency. Additionally, the asset dependence structure exhibits increased heterogeneity across investment horizons after the COVID-19 outbreak, with short-term structures demonstrating higher volatility, while medium- and long-term structures show similarity. Finally, by generating a dynamic energy portfolio, this paper measures the investment allocation weights of each asset before and after the emergence of COVID-19. Findings indicate an increased need for investment in natural gas, crude oil, and clean energy post-COVID-19 outbreak, suggesting a reduction in coal investment. The analyses aim to assist energy investors in enhancing their economic decision-making processes and refining their portfolio management strategies.

Dynamic graph reinforcement learning algorithm for portfolio management: A novel time–frequency correlated model

Revealing the dynamic correlations among various assets is crucial for portfolio management. In this study, we build a novel Multi-graphs representation based on wavelet coherence to capture and learn their dynamic time–frequency correlations. Then, a novel portfolio management strategy is proposed by integrating the Multi-graphs representation with the deep reinforcement learning algorithm, referred to as the Dynamic Wavelet Coherence Graph Convolutional Reinforcement Learning (WCG-RL) algorithm. Several numerical experiments fully illustrate the performance of our proposed WCG-RL algorithm is applicable to stocks with different market capitalization, and its performance surpasses that of the state-of-the-art algorithms in the Chinese stock market.

Capital Allocation Analysis based on Markowitz Model and Index Model

In finance, the question of how best to invest money to make more money is not an easy one. Some academics and hands-on practitioners have studied into this field for decades. This article delves into this issue, with a special focus on a detailed analysis of various investment plans. To get a better idea of which plan is better in a given situation, this paper dug through a bunch of data that included ten different company stocks from various industries, as well as daily revenue data for the S&P 500 over a 20-year history. This paper mainly looked at two key investment plans: the Markowitz model and the Index model. This paper did some simple math and theoretical research, and then this paper used the capabilities of Excel to help us find the best solution. And the analysis specially adopted a monthly summary method, minimized the complexity of the data on a horizon. And the study critically evaluating investment strategies within real-world constraints such as Regulation T, arbitrary "box" constraints, and scenarios involving no short positions or exclusion of broad indices.The finding shows that the performance of the assets chosen by Markowitz is better than Index Model under the given circumstances, which indicates the more complex model and addition data could probably provide a better result. This dissertation aims to contribute significantly to the field of finance by enhancing the understanding of portfolio management strategies, thus aiding in informed decision-making in the ever-evolving financial landscape.

Optimizing Cryptocurrency Portfolios: A Comparative Study of Rebalancing Strategies

Objective – This study aims to contribute to the field of cryptocurrency portfolio management and rebalancing strategies by empirically investigating the impact of different allocation frequencies and threshold percentages on the risk-adjusted returns of cryptocurrency portfolios. Methodology/Technique – Utilizing a simulation of 10,000 cryptocurrency portfolios comprising seven assets, including Ethereum (ETH), Bitcoin (BTC), Tether (USDT), Litecoin (LTC), Solana (SOL), Dogecoin (DOGE), and Polygon (MATIC), this study examines and compares the effects of different allocation frequencies (daily, weekly, and monthly) in time-based rebalancing and various threshold percentages (5%, 10%, and 15%) in threshold-based strategies on the portfolios' risk-adjusted returns, using the Sharpe ratio. The performance of these strategies is also compared with a passive buy-and-hold strategy. Findings –The research reveals statistically significant differences in the risk-adjusted returns between the buy-and-hold strategy and the daily rebalancing and threshold-based strategies with 5% and 10% threshold percentages. The daily rebalancing strategy demonstrates a higher Sharpe ratio, while lower threshold percentages lead to better risk-adjusted returns. Novelty – These empirical findings, using a simulation of 10,000 cryptocurrency portfolios, provide valuable insights into optimizing cryptocurrency portfolio performance through rebalancing strategies. Additionally, they highlight the effectiveness of implementing rebalancing techniques in cryptocurrency portfolios, contributing to the understanding of rebalancing optimization in this domain. Type of Paper: Empirical JEL Classification: G11, G19. Keywords: Cryptocurrency; Mean-Variance Optimization; Portfolio Management; Rebalancing Strategies; Risk-Adjusted Returns Reference to this paper should be made as follows: Sornmayura, S; Sakolvieng, N; Numgaroonaroonroj, K. (2024). Optimizing Cryptocurrency Portfolios: A Comparative Study of Rebalancing Strategies, J. Fin. Bank. Review, 8(4), 01 – 16. https://doi.org/10.35609/jfbr.2024.8.4(1)

Monte carlo simulation with bilstm for day-ahead stock portfolio management

<div>Predicting stock price movement and optimizing day-ahead stock portfolios are challenging tasks due to the inherent complexity and volatility of financial markets. This study proposes a novel approach that combines bidirectional long short-term memory (BiLSTM) neural networks with monte carlo simulation (MCS) to enhance day-ahead stock portfolio management. In the proposed methodology, historical data of the top-performing 10 stocks from different sectors of the National Stock Exchange of India (NSEI) is obtained from 1 January 2004 to 30 June 2023 and utilized to train a BiLSTM model. This model effectively extracts intricate patterns and trends from the time series, leading to more accurate and robust stock price predictions. MCS generates different scenarios, considering various market conditions and uncertainties. These scenarios provide a comprehensive view of the portfolio’s performance under different conditions, thus mitigating the risk of relying solely on a single prediction. The study evaluates the proposed framework and compares its performance against traditional portfolio management strategies. Results demonstrate that the MCS with the BiLSTM approach outperforms traditional methods in terms of risk-adjusted returns and portfolio stability.</div>

What are tenants demanding the most? A machine learning approach for the prediction of time on market

PurposeThis is the first article to apply a machine learning approach to the analysis of time on market on real estate markets.Design/methodology/approachThe random survival forest approach is introduced to the real estate market. The most important predictors of time on market are revealed and it is analyzed how the survival probability of residential rental apartments responds to these major characteristics.FindingsResults show that price, living area, construction year, year of listing and the distances to the next hairdresser, bakery and city center have the greatest impact on the marketing time of residential apartments. The time on market for an apartment in Munich is lowest at a price of 750 € per month, an area of 60 m2, built in 1985 and is in a range of 200–400 meters from the important amenities.Practical implicationsThe findings might be interesting for private and institutional investors to derive real estate investment decisions and implications for portfolio management strategies and ultimately to minimize cash-flow failure.Originality/valueAlthough machine learning algorithms have been applied frequently on the real estate market for the analysis of prices, its application for examining time on market is completely novel. This is the first paper to apply a machine learning approach to survival analysis on the real estate market.

Short-Term Versus Long-Term Portfolio Management Strategies and the Selection of Securities

Purpose: This study examines the effectiveness of short-term versus long-term portfolio management strategies and the selection of securities. It aims to provide insights into how different strategies impact investment performance, considering risk tolerance and financial goals. Research Design and Methodology: The study synthesizes findings from academic journals and empirical research using a qualitative literature review approach. The methodology involves thematic analysis to identify key themes, patterns, and insights related to portfolio management strategies and security selection. Findings and Discussion: The research highlights that short-term strategies like momentum trading can capitalize on transient market inefficiencies but entail higher transaction costs and volatility. Conversely, long-term strategies, such as value investing, focus on fundamental analysis and offer more stable returns over time. The integration of ESG criteria into security selection is shown to enhance portfolio performance and align investments with sustainability objectives. Behavioral biases and technological advancements also significantly influence portfolio management decisions. Implications: The study underscores the importance of balancing short-term and long-term strategies based on investor risk tolerance and financial goals. Financial practitioners can leverage these insights to design diversified portfolios and offer tailored advice. Future research should explore the dynamic interplay between these strategies and the impact of technological and regulatory changes on portfolio management. Integrating ESG considerations is crucial for sustainable investing and aligning with evolving market dynamics.

Investment Weightings of Technology and Traditional Stocks: Investor Choice and Risk Management

In the era of big data, the financial landscape is undergoing transformative changes through the integration of advanced technologies. This research delves into the dynamic realm of asset portfolios within the information technology industry, traditional sectors, and amalgamated portfolios containing popular giant stocks. Employing Python and machine learning, the study focuses on predicting expected returns, comparing and analyzing diverse portfolios to identify optimal investment strategies for risk management. Evaluation metrics include annual return, annual volatility, Sharpe ratio, and statistical charts. The findings highlight the lucrative potential of investing in the information technology sector, revealing an impressive annual return rate of 40.1%. In contrast, traditional industry portfolios not only underperform but also exhibit high-risk profiles and diminished returns. This research underscores the critical role of technological advancements and data-driven methodologies in shaping contemporary financial strategies for robust portfolio management. his research advocates for the strategic incorporation of technology-driven insights in financial decision-making, emphasizing the significant outperformance potential of information technology portfolios in navigating the complexities of modern investment.

Exploring fluctuations and interconnected movements in stock, commodity, and cryptocurrency markets

Abstract This research employs a vector autoregression (VAR) analysis to explore the volatility and dynamic interactions between stock, commodity, and cryptocurrency markets. It focuses on the returns of the S&P 500, gold, crude oil, and Bitcoin to analyse their interconnections. Our results indicate that Bitcoin returns positively affect S&P 500 and crude oil, but negatively impact gold. Conversely, crude oil returns have a positive influence on gold but lead to decreased returns for Bitcoin and the S&P 500. Similarly, higher gold returns correspond to increased returns in crude oil and S&P 500 but decreased returns in Bitcoin. The rise of the S&P 500 negatively influences Bitcoin and crude oil returns, while gold returns remain unaffected. However, these relationships exhibit weak and limited strength. Including these assets in a portfolio can help risk mitigation, as Bitcoin diversifies crude oil, gold, and S&P 500, and crude oil diversifies S&P 500. These findings contribute to our understanding of global financial dynamics and inform decision-making in risk assessment, portfolio management, risk mitigation, and diversification strategies.