Portfolio Management Model Research Articles

Risk parity portfolio optimization under heavy‐tailed returns and dynamic correlations

Risk parity portfolio optimization, using expected shortfall as the risk measure, is investigated when asset returns are fat‐tailed and heteroscedastic with regime switching dynamic correlations. The conditional return distribution is modeled by an elliptical multi‐variate generalized hyperbolic distribution, allowing for fast parameter estimation via an expectation‐maximization algorithm, and a semi‐closed form of the risk contributions. A new method for efficient computation of non‐Gaussian risk parity weights sidesteps the need for numerical simulations or Cornish–Fisher‐type approximations. Accounting for fat‐tailed returns, the risk parity allocation is less sensitive to volatility shocks, thereby generating lower portfolio turnover, in particular during market turmoils such as the global financial crisis or the COVID shock. While risk parity portfolios are rather robust to the misuse of the Gaussian distribution, a sophisticated time series model can improve risk‐adjusted returns, strongly reduces drawdowns during periods of market stress and enables to use a holistic risk model for portfolio and risk management.

Comparative Analysis of the Markowitz Model and the Kraljic Matrix Model in Portfolio Optimization and Procurement Management

This research studied two important models of portfolio management: the Markowitz model and the Kraljic Matrix Model. The Markowitz model is the basis of modern portfolio theory and is designed to optimise asset allocation by minimising risk while maximising returns. This paper provides a system to build a balanced portfolio by utilising diversity. On the other hand, the Kraljic Matrix Model classifies products based on supply risk and profit impact and provides a strategic tool for purchasing management. This model categorises products into four categories: noncritical, leverage, strategy, and bottleneck to support informed purchasing decisions. Despite its usefulness, the Kraljic matrix has been criticised for not taking into account the supplier’s perspective and for not providing guidelines for managing the movement of goods within the matrix. This paper studies the application and limitation of the two models, emphasises the need to adapt to the strategy in the portfolio and procurement management, and adjust according to the market dynamics.

An Overview of Optimization Models for Portfolio Management

An Overview of Optimization Models for Portfolio Management

Re-examining China and the u.s.’s respective green bond markets in extreme conditions: Evidence from quantile connectedness

This study explores the role of green bonds in mitigating risks during extreme conditions, considering China and the US’ robust green bond markets and global risk events. It analyzes the interconnectedness of green bonds with other sectors like conventional bonds, equities, crude oil, and monetary policy. Using the quantile connectedness approach, it reveals how stabilized green bond markets in both countries act as hedges during extreme situations. By examining time-varying spillover effects, it identifies commonalities and differences in linkages between green bond markets and other sectors. These findings endorse green bonds’ integration into finance and hold implications for enhancing portfolio management and risk models.

Comparative Analysis of Portfolio Management Models: Markowitz, CAPM, and Multi-Factor Models

This paper presents a comparative analysis of three foundational portfolio management models: the Markowitz Efficient Frontier, the Capital Asset Pricing Model (CAPM), and Multi-Factor Models. It aims to explore their theoretical foundations, empirical applicability, and practical usage to assess their strengths and limitations in financial portfolio management. The Markowitz model is appreciated for its detailed risk-return optimization framework but criticized for its reliance on historical data and computational demands. The CAPM simplifies risk assessment through market beta, yet its assumptions of market efficiency and a risk-free rate are viewed as impractical under current market conditions. Multi-Factor Models address some limitations of the CAPM by incorporating various risk factors, offering enhanced explanatory power but also adding complexity in factor selection.The study concludes that while no single model is universally superior, the choice of model should depend on the specific needs of the portfolio manager, including risk-return objectives and market environment. The paper suggests a blended or adaptive approach to model selection, highlighting the need for flexibility in response to evolving market dynamics and advances in computational finance.

An extension analysis of Amihud's illiquidity premium: Evidence from the Taiwan stock market

This study proposes a novel illiquidity measure that excludes overnight returns and incorporates the recency effect, and investigates whether this new metric more effectively captures the illiquidity premium in the Taiwan stock market relative to Amihud's (2002) measure and other illiquidity measures that exclude overnight returns or account for the recency effect. Cross-sectional and time-series asset pricing tests reveal that our measure dominates other illiquidity measures, yielding a more profitable long–short strategy. Vector autoregressive analysis confirms these results for the aggregate market. Our study contributes to the measurement of liquidity in emerging markets and suggests potential improvements for portfolio management and asset pricing models.

Dynamic Mean–Variance Portfolio Optimization with Value-at-Risk Constraint in Continuous Time

Recognizing the importance of incorporating different risk measures in the portfolio management model, this paper examines the dynamic mean-risk portfolio optimization problem using both variance and value at risk (VaR) as risk measures. By employing the martingale approach and integrating the quantile optimization technique, we provide a solution framework for this problem. We demonstrate that, under a general market setting, the optimal terminal wealth may exhibit different patterns. When the market parameters are deterministic, we derive the closed-form solution for this problem. Examples are provided to illustrate the solution procedure of our method and demonstrate the benefits of our dynamic portfolio model compared to its static counterpart.

Portfolio construction using explainable reinforcement learning

AbstractWhile machine learning's role in financial trading has advanced considerably, algorithmic transparency and explainability challenges still exist. This research enriches prior studies focused on high‐frequency financial data prediction by introducing an explainable reinforcement learning model for portfolio management. This model transcends basic asset prediction, formulating concrete, actionable trading strategies. The methodology is applied in a custom trading environment mimicking the CAC‐40 index's financial conditions, allowing the model to adapt dynamically to market changes based on iterative learning from historical data. Empirical findings reveal that the model outperforms an equally weighted portfolio in out‐of‐sample tests. The study offers a dual contribution: it elevates algorithmic planning while significantly boosting transparency and interpretability in financial machine learning. This approach tackles the enduring ‘black‐box’ issue and provides a holistic, transparent framework for managing investment portfolios.

Comparative Analysis of S&P 500 and NASDAQ Indices: A Machine Learning Approach to Understanding Differential Market Sensitivities and Growth Stock Dynamics

This paper delves into the implementation of a Walking Forward Machine Learning Model designed for the construction and forecasting of portfolios comprised of randomly selected stocks from the S&P 500 and NASDAQ indices. The primary objective of the study is to scrutinize the attributes of technology stocks, specifically assessing whether they exhibit characteristics typical of growth stocks. Furthermore, the research aims to discern potential disparities in predictive characteristics between technology stocks and standard equities. The passage elucidates the research methodology, encompassing data collection, model establishment, and evaluation processes, along with insights into the intricacies of portfolio construction. The empirical findings shed light on the model's efficacy in predicting stock returns and its aptitude in crafting investment portfolios. The concluding remarks underscore the significance of adjusting the model's learning rate in accordance with the distinct traits of various markets, emphasizing the need for a nuanced approach to enhance its overall generalization performance. This study contributes valuable insights into optimizing machine learning models for effective portfolio management in dynamic financial markets.

Implementation of value-oriented project portfolio management for the development of complex system

ObjectivesThe aim of the article is to set the problem of forming the optimal value-oriented portfolio of the development of a complex system, taking into account the mutual influence of the components of the portfolio on each other.Material and methodsThe research used: project portfolio management methods; systems theory and system analysis (for the formalization of value-oriented management processes); mathematical modeling tools (for the formation of basic models of portfolio management).ResultsThis article provides a basic methodological framework for portfolio management of organizational development. The conceptual framework for portfolio management has been formalized, where portfolio management processes are considered as a means of implementing strategic decisions.ConclusionsThe success of development portfolio management should not only be measured by the economic component, but also by the values that influence the sustainable development of the region. The current legal framework for the design and implementation of public projects in Ukraine is not up to date, as confirmed by the findings of international experts and domestic scientists.

Deep Reinforcement Learning Model for Stock Portfolio Management Based on Data Fusion

Deep reinforcement learning (DRL) can be used to extract deep features that can be incorporated into reinforcement learning systems to enable improved decision-making; DRL can therefore also be used for managing stock portfolios. Traditional methods cannot fully exploit the advantages of DRL because they are generally based on real-time stock quotes, which do not have sufficient features for making comprehensive decisions. In this study, in addition to stock quotes, we introduced stock financial indices as additional stock features. Moreover, we used Markowitz mean-variance theory for determining stock correlation. A three-agent deep reinforcement learning model called Collaborative Multi-agent reinforcement learning-based stock Portfolio management System (CMPS) was designed and trained based on fused data. In CMPS, each agent was implemented with a deep Q-network to obtain the features of time-series stock data, and a self-attention network was used to combine the output of each agent. We added a risk-free asset strategy to CMPS to prevent risks and referred to this model as CMPS-Risk Free (CMPS-RF). We conducted experiments under different market conditions using the stock data of China Shanghai Stock Exchange 50 and compared our model with the state-of-the-art models. The results showed that CMPS could obtain better profits than the compared benchmark models, and CMPS-RF was able to accurately recognize the market risk and achieved the best Sharpe and Calmar ratios. The study findings are expected to aid in the development of an efficient investment-trading strategy.

Optimization of Portfolio Management Models with Indexed Stocks on the Lima Stock Exchange

Investment fund managers are limited by the fact that Latin American financial markets offer very few investment possibilities, which forces them to carry out operations at a global level. The objective is to optimize the portfolio management models with indexed stocks in the Lima Stock Exchange (27 stocks considering 2082 days from January 02, 2014 to April 13, 2022) applying the Markowitz models that determine the portfolios of the frontier of investment possibilities. The Sharpe model (CAPM), which calculates the expected return considering systemic risks, and the Sharpe index, which measures the stock return with total risk. Finally, the Black-Litterman (BL) model adjusts the ex-post expected return with expert opinion. By comparing the BL/CAPM ratio, an index is obtained that improves the predictability of expected returns and it is observed that the efficiency of this indicator is greater than the Sharpe index of subsequent expected returns (Sharpe BL). Therefore, the hypothesis that optimizing the portfolio management models improves the predictability of the expected returns of the indexed shares of the Lima Stock Exchange is accepted.
 
 Received: 23 July 2023 / Accepted: 10 January 2024 / Published: 5 March 2024

A Deep Reinforcement Learning Model for Portfolio Management based on Weight Adjustment

Existing portfolio management models based on deep reinforcement learning adjust funds dynamically by constructing an action space with specific trading behaviors. However, this method cannot effectively adapt to complex investment environments. This paper proposes an LSTM-ER-DCPPO portfolio management model based on the improved PPO algorithm. The model provides stable policy learning, enhanced strategy exploration, and trend identification, enabling more precise capital allocation through continuous asset weight output. To evaluate the model, a simulated market trading environment based on real stock data was created. The experimental results show that the LSTM-ER-DCPPO model achieved an annualized return of 58.62%, a maximum drawdown of 8.53%, a Calmar ratio of 6.873, and a Sharpe ratio of 2.434, outperforming other benchmark models.

Comparative Analysis and Research of Investment Portfolio Management Models

Portfolio management plays a significant role in the world of finance and investing, offering benefits and contributions to both individual investors and institutions. Researchers use many mathematical models to make informed decisions about how to allocate and manage investments within a portfolio to optimize risk versus return trade-off based on the investors preference and constraints. This paper primarily employs the literature review methodology and comparative analysis methodology. Firstly, it collects, summarizes, and analyzes multiple papers on portfolio management models, including Markowiz Mean-Variance Model, Capital Market Line (CML), Arbitrage Pricing Theory (APT) and Capital Asset Pricing Model (CAPM) with the origin of the models, their key assumptions, components, and applications. Additionally, this paper also utilizes comparative analysis by comparing the similarities, differences, and respective downsides and benefits of the four main research models. Through this comparison, the paper investigates the relationships and application distinctions among the models. As a result, these models evolve and refine over time, with some building on others. CAPM extends the Markowitz Model by introducing the risk-free rate and market portfolio as benchmarks, simplifying the risk-return relationship, and introducing systematic risk. The Capital Market Line (CML), derived from CAPM, illustrates efficient portfolios made up of both market and risk-free assets and shows the risk-return trade-off. APT, a later model, can be seen as an extension of CAPM.

The application of blockchain and robo-advisors in wealth management literature review

This paper aims to study the blockchain in the field of financial ecology as the carrier, optimize the consensus mechanism, and use intelligent consulting as an analytical means to provide investors with an objective, low-cost asset allocation portfolio. This article begins with an introduction to the features of blockchain decentralization and tamper-proof execution of algorithms, how proof-of-work works, and how tokens can improve welfare and reduce user base volatility. The paper then introduces how robo-advisors work and how they develop. Finally, this paper reviews existing research models on robo-advisors, from the traditional mean-variance model based on Markowitz to the jump-diffusion, regime-switching model, and the Pi portfolio management model that does not require quantifying risk preference coefficients, which this paper discusses and seeks to explore the advantages and limitations between the different models. Based on the existing research gaps, the directions that digital finance can expand in the future are discussed.

An agile portfolio management model for the insurance sector: the APMI model

Nowadays, the increasing uncertainty and instability make it crucial for traditional companies to become more agile and able to act fast on consumer needs and expectations. Therefore, many insurance companies are seeking to increasingly adopt Agile practices to become more effective, faster, and leaner in their critical processes. On the other hand, several companies are strengthening their planning methodologies by implementing Portfolio Management models. These models enable them to manage their initiatives in a more integrated and efficient manner that is strategically aligned, minimizes complexity, and provides higher flexibility when responding to uncertainty. Given the limited scientific knowledge in combining Agile and Portfolio Management (PfM), particularly in the insurance industry, a new Agile Portfolio Management (APfM) model, the APMI – Agile Portfolio Management for insurers was designed and tested, showing how Agile and PfM international practices can be conciliated with current insurance industry-specific practices. Results revealed a high satisfaction level with the model implementation, indicating that the proposed model can foster a greater strategic alignment, increase the organization’s strategic focus, promote transversal alignment and visibility, and support the organization’s capacity coordination.

Passive Investment: The Political Dynamics of Charter Expansion in Los Angeles’ Portfolio District

Since the 1990s, charter schools have spread rapidly across the nation. The replication and expansion of charter schools has become a common feature of the portfolio management model which situates the district as strategic manager of a choice-based system including traditional and charter schools. Yet, many school districts have experienced substantial political, logistical, and technical challenges in managing and “right-sizing” the charter sectors in their communities. The Los Angeles Unified School District presents a strategic case to examine the challenges of charter expansion in a portfolio management model district. Using a micropolitical lens, we examine how political tensions over charter schools in Los Angeles affected one expanding charter network in LAUSD. This 3-year case study draws on interviews and focus groups with 48 charter leaders, teachers, and parents. We find that broader political tensions over charter schools in Los Angeles affected the network in material ways that challenge important assumptions of the functioning of LAUSD’s portfolio model. Specifically, we find that political tensions between the network and the district challenge a central assumption of the portfolio approach: namely, that the portfolio district can effectively operate as a neutral manager optimizing performance across schools in the portfolio. These political tensions also affected how this charter network managed instructional practice and parent engagement. This analysis offers important dimensionality to our understanding of organizational responses in portfolio district settings.

UNCERTAINTY MANAGEMENT IN PRODUCT DEVELOPMENT PORTFOLIOS: THE IMPACT OF GLOBAL SUSTAINABILITY AGENDAS

AbstractIncreased focus on sustainability significantly impacts product development portfolio management in organizations. This paper focuses on the significant unaccommodated uncertainty caused by the green transition for current mid- and long-term portfolio management processes. These uncertainties arise in areas such as the regulatory environment, market demands, and technical capabilities. This paper makes four contributions: First, current product portfolio management literature is mostly employing deterministic practices. Uncertainties are incompletely addressed, and current methods fail to address the deep uncertainties of the green transition. Second, building a literature-based conceptual framework of the sources of uncertainty in 6 areas: Business Models, Technology, Regulation and Legislation, Finance and Insurance, Market and Consumer, and Organizational Context. Third, preliminary empirical evidence supports the usefulness of our model for product development portfolio management. Fourth, concluding with a suggested empirical research agenda to develop a deeper understanding of challenges towards method and theory development to support the green transition on the portfolio management level.

STRATEGIC MANAGEMENT OF THE PORTFOLIO OF FINANCIAL ASSET

Until now, three approaches to asset portfolio management have been used. The first approach is the classic one, based on the "Efficient Market Hypothesis" (EMH). The second and more modern approach is related to the "Fractal Market Hypothesis" (FMH). Modern economic practice is characterized by the presence of structurally unstable markets, included as nodes in the network of the world economy, which functions in real time. The structure of the available financial instruments is heterogeneous and non-Markovian processes arise in them. The third approach is the formation of a dynamic strategy of investment management of the asset portfolio. Due to the complex structure of the modern global financial market, the heterogeneous structure of available financial instruments and traders using different approaches and time horizons, forecasts, as a rule, require a large number of observations, work poorly at the edges of bifurcations, and do not have a computer model that could build forecasts in real time. In these structures, slow diffusion-type processes with a memory phenomenon occur, i.e., non-Markovian processes. Therefore, the formation of a dynamic strategy using modern methods of mathematical and computer modeling is very promising.
 Real financial data is expressed in rational numbers. Computational models were developed on the basis of classical substance analysis. Therefore, p-adic analysis methods are increasingly used in financial mathematical modeling. These methods are used, in particular, in the construction of neural networks, cellular automata, and percolation models. The paper seems to have taken the first step towards building a "synthetic" model of dynamic asset portfolio management. The model has the form of a differential equation in fractional derivatives obtained using the so-called interbasin kinetics method. A general form of the energy market model is also offered, as one of the specific, especially nowadays, markets.

Prioritization Model for IT Project Portfolio Management in Private University: A Literature Review

The swift progress of technology can be harnessed to address the increasing demand for projects, particularly in various organizations like private universities that must cope with resource limitations and make critical decisions. Information Technology (IT) encompasses any technology, such as equipment or techniques, employed by businesses, institutions, or other organizations to process information, including computing, telecommunications technologies, consumer electronics, and broadcasting, as it increasingly digitizes. Choosing between dozens or hundreds of project alternatives presents complex multi-criteria decision-making problems for an organization's portfolio and priorities, necessitating clear-cut techniques, methods, and factor definitions for prioritizing decision-making. This literature review formulates the problem, specifically identifying the criteria for comparison and prioritization models, and seeks a framework and methodology for prioritizing portfolio management in private organizations, particularly universities. The literature review identifies the characteristics of private organizations and the methodologies and practices employed in researching the application of portfolio management priorities and explores the use of portfolio management techniques from prior studies tested in practice and project priority methodologies in private services. The results contribute to enhancing theories on techniques, methods, and, particularly, portfolio project management priorities for the private sector.