Asset Portfolio Research Articles

Curriculum learning empowered reinforcement learning for graph-based portfolio management: Performance optimization and comprehensive analysis

Portfolio management (PM) is a popular financial process that concerns the occasional reallocation of a particular quantity of capital into a portfolio of assets, with the main aim of maximizing profitability conditioned to a certain level of risk. Given the inherent dynamicity of stock exchanges and development for long-term performance, reinforcement learning (RL) has become a dominating solution for solving the problem of portfolio management in an automated and efficient manner. Nevertheless, the present RL-based PM methods just take into account the variations in prices of portfolio assets and the implications of price variations, while overlooking the significant relationships among different assets in the market, which are extremely valuable for managerial decisions. To close this gap, this paper introduces a novel deep model that combines two subnetworks; one to learn a temporal representation of historical prices using a refined temporal learner, while the other learns the relationships between different stocks in the market using a relation graph learner (RGL). Then, the above learners are integrated into the curriculum RL scheme for formulating the PM as a curriculum Markov Decision Process, in which an adaptive curriculum policy is presented to enable the agent to adaptively minimize risk value and maximize cumulative return. Proof-of-concept experiments are performed on data from three public stock indices (namely S&P500, NYSE, and NASDAQ), and the results demonstrate the efficiency of the proposed framework in improving the portfolio management performance over the competing RL solutions.

Correlated spatiotemporal downscaling of Euro‐CORDEX climatic data for infrastructure resilience assessment

AbstractA methodology is presented for downscaling the Euro‐CORDEX climatic projections in order to derive spatially and temporally correlated weather fields that can be used for risk and resilience assessment of large‐scale asset portfolios or interconnected infrastructure. The temporal resolution of the Euro‐CORDEX data is downscaled to a 10 min basis by employing a modified analogue‐type approach that utilizes the k‐NN algorithm along with measurements from weather stations. The aim is to generate composite “Frankenstein” days comprising 144 jigsaw pieces of observed 10 min timeseries that are scaled and/or shifted, and matched together to form a continuous daily record. These point‐estimates, valid only at the locations of the weather stations, are expanded spatially by employing high‐fidelity weather intensity measure fields that provide variable yet synchronous patterns of weather parameters at all locations of interest. As a case study, the Euro‐CORDEX projections for wind, temperature, and precipitation are downscaled for the Metsovo‐Panagia segment of Egnatia Odos highway in Greece, by employing high‐fidelity Computational Fluid Dynamic simulations that account for the topography of the site to simulate turbulent wind flows. These are combined with measurements of two local weather stations to generate the Frankenstein timeseries and corresponding weather fields that can be used for estimating operability, recovery and direct/indirect loss statistics on an event‐by‐event basis for an ensemble of interconnected highway assets.

Economic Feasibility of LNG Business: An Integrated Model and Case Study Analysis

Liquefied natural gas (LNG), recognized as the fossil fuel with the lowest carbon emission intensity, is a crucial transitional energy source in the global shift towards low-carbon energy. As the natural gas industry undergoes rapid expansion, the complexity of investment business models has increased significantly. Optimizing the combination of various segments within the value chain has become standard practice, making it essential to control risks and enhance economic benefits in these multifaceted scenarios. This paper introduces an integrated economic model encompassing upstream, liquefaction, shipping, regasification, and consumption, suitable for both upstream and downstream integration. The model offers a comprehensive analysis of the primary business models and key factors across each segment of the value chain. By constructing a robust economic evaluation framework, the study aims to provide a holistic approach to understanding the economic feasibility of LNG projects. Two detailed case studies are conducted to demonstrate the application and effectiveness of the proposed model, highlighting its capability to guide investment decisions, support risk management, and optimize asset portfolios. The integrated economic model developed in this study serves as a valuable tool for stakeholders in the LNG industry. It not only facilitates informed investment decision-making but also enhances the strategic management of risks and resources. By leveraging this model, investors and managers can better navigate the complexities of the LNG business, ensuring sustainable and economically viable operations.

Gold characteristics as safe haven and assets diversification for Sharia stocks in Indonesia

Purpose This study aims to determine the role of gold as a safe haven, hedge and asset diversification for Shariah stock in conditions of extreme stock market declines. Design/methodology/approach Quantitative approach is used by applying the threshold generalized autoregressive conditional heteroskedasticity (TGARCH) model to capture bad or good news in the market condition and quantile regression method to obtain the extreme values of stock returns in several market conditions. The data used were the daily closing price of gold and the Jakarta Islamic Index from January 2011 to October 2022. Findings The average conditions show gold does not have a hedge property and only acts as an asset diversification. Second, gold has a substantial, safe haven property in every economic condition. However, the safe-haven property of gold seemed to weaken during the most extreme stock market decline. Thus, although gold appears as a safe haven and asset diversification, it remains a risky investment and only provides a minor role in the face of the extreme stock market period. Practical implications This research provides a discourse and literature for Islamic investors and investor managers to choose the right investment instrument in various economic conditions where gold has a function as diversification and safe haven in their asset portfolio under any other asset portfolio conditions which is also in line with modern portfolio theory. For policymakers, the study can be used as material for consideration in making policies related to the accessibility of gold as an investment instrument. Originality/value This study presents the originality by using the price of Antam gold as a proxy for gold investment during the latest research year data and focusing on case studies in Islamic capital market in Indonesia. Moreover, this research provides quantile regression that sharply discussion in various economics condition.

Analysis of Information Technology Strategy in Multifinance Companies Based on Digital Present Information Website

Technology is needed both in the process of collecting data, information and activities to reduce the use of paper or paperless. According to OJK, a Financing Institution is a business entity that carries out financing activities in the form of providing funds or capital goods. Some of the benefits of IT strategy Making a roadmap for IT development and development both related to infrastructure, application systems, services and information security. With the data and information that can be collected, it can be managed and used in decision making through an analysis that can be used in looking at the policies and strategic decisions of the organization. With the IT strategy, companies can have strategies in securing data and system management in the organization, in particular, with the IT strategy, it can be used to segment the market and determine business focus to increase added value that can be provided to consumers or debtors. From making a checklist using the websites of 26 finance companies, it can be seen that the company's strategy in digitalization and information technology such as having applications, ISO 270001 standards, using marketing and payment channels as well as the use of financing glorification forms and financing applications shows that multifinance companies have begun to move to digitalization. If a multifinance company has an aggressive vision for asset development and digital present, digital channels are enhanced to increase the number of potential new customers entering through digital channels and of course by improving and maintaining data quality by using third party data and increasing payment channel cooperation to ensure more choice of debtor payments. With a moderate vision, the use of third party data to improve credit quality to improve or improve the quality of the asset portfolio of multifinance companies.

The role of alternative investments in Brazilian portfolios

This paper assesses the impact of alternative assets on the performance of Brazilian asset portfolios. Although alternative assets are largely studied throughout the world, that is not the case for Brazil as there are just a few studies on the topic. As the Brazilian capital markets are growing at a fast pace, the high correlated aspect of the market calls for measures to ensure balanced returns for the long run, therefore, the insights of the study may support investors during the process of asset allocation. In this study the alternative assets were divided into two categories: Brazilian alternative assets and international alternative assets. Performance measures were obtained from a portfolio comparison and through a Markowitz frontier analysis. The results show that adding alternative assets (Brazilian or international) to a portfolio usually generates higher returns with lower risks, leading to better risk adjusted results and an overall more balanced portfolio.

Development of an AI framework using neural process continuous reinforcement learning to optimize highly volatile financial portfolios

High volatility presents considerable challenges in the optimization of financial portfolio assets. This study develops and explores model-based reinforcement learning (MBRL) in this context. Existing literature suggests that while model-free approach offers certain computational advantages, it frequently fails to encapsulate the nature of highly dynamic capital markets. This limitation is due to an insufficient consideration of the interactions between agents and environmental states within the reinforcement learning framework. Conversely, MBRL encounters inaccuracies representing stochastically evolving states typical of volatile capital markets. To address these limitations, we introduce an innovative AI framework in the MBRL domain by integrating attentive neural processes with continuous-time MBRL. This novel approach, termed Neural Process Continuous Reinforcement Learning (NPCRL), is posited to enhance the ability of MBRL to adapt to volatile fluctuations in capital markets. The effectiveness of NPCRL is empirically evaluated through a series of experiments using three important performance indicators of financial portfolios: returns, risk, and drawdown recovery. The results demonstrate that NPCRL surpasses other methods in achieving a balanced trade-off between long-term returns and risk management. This study advances our understanding of machine learning development by suggesting methods that are more proficient at capturing and adapting in volatile training environments.

Dynamic dependence and spillover among the energy related ETFs: From the hedging effectiveness perspective

Due to the fundamental position of energy, the dynamics of the energy ETF markets are of great interest when facing unexpected event shocks. To explore the volatility spillovers within the energy ETF market and with other related markets under event shocks, we use the PCA method to extract macroeconomic factor series (ME) from four types of ETF return series. Then, we apply the DCC-GARCH-Copula model to analyze the dynamic correlation between the energy EFTs and the MEs as well as the related ETFs. Finally, the TVP-VAR-DY index is used to explore the spillover relationship between these markets in terms of spillover impact. The findings suggest that the clean energy ETFs have a greater volatility pass-through to real estate, while the volatility pass-through of energy ETFs to gold is stronger in all cases. Total connectivity in these markets exhibits different performances at different stages during the sample period, reaching its peak during the global COVID-19. These findings support investors to adjust their asset portfolios in a timely manner in the face of shocks while helping regulators strategize more effectively.

Financing constraints, major business performance, and return on financial assets

This study systematically examines the relationship between financing constraints and the return on corporate financial assets based on data from Chinese listed companies from 2012 to 2022. It found a positive correlation between the risk and return of financial asset portfolios; higher risk leads to higher return. Firms with fewer financing constraints have better returns on financial assets. A decrease in return on a firm's operating assets often coincides with an increase in return on financial assets.

"Blood on the floor:" The nickel commodity frontier and inter-capitalist competition under green extractivism

Major companies in the mining industry are strategizing to benefit from the expected rise in demand for energy "transition minerals" that underpin current technologies of decarbonization (such as batteries and wind turbines). This article elucidates their current strategies of accumulation through the case of BHP, the world's largest mining company. We draw on political ecology and commodity frontier theory in order to grapple with inter-capitalist competition under the current moment of green extractivism by examining firm and state practices in the nickel commodity frontier. Empirically, we examine the changing role that nickel has played in BHP's asset portfolio during the past decade where it has attempted to significantly accumulate from the expansion of the nickel commodity frontier. Yet, despite this centering of the expansion of the nickel commodity frontier for its particular strategy of accumulation under green extractivism, it has so far been unsuccessful. Given this potential for failure of company practices in commodity frontiers, we argue that green extractivism should not always and everywhere be seen as a story foretold.

Portfolio Analysis of Five Stocks Under Different Constraints Based on Markowitz Model & Index Model

Since the dawn of the 21st century, while there has been an abundance of talented fund managers, truly exceptional asset portfolios have been rare. Addressing this phenomenon, the study delves into the current state of asset management, employing two renowned financial models: the Markowitz model and the Index model. These models are utilized to analyze the returns and risks of five high-performing assets. Additionally, acknowledging the diversity of investor preferences, this paper incorporates five different constraints to cater to a wider spectrum of client needs. The crux of the research is the optimization of the asset portfolio, grounded in these models and constraints. The paper findings indicate that the integration of the Markowitz and Index models with the capital market line and the efficient frontier proves highly effective in the management of risk asset portfolios. In this paper, the Markowitz model consistently excels over the index model in both minvariance and maxsharpe scenarios. This study has important reference value for investors in related fields.

A Stochastic Decision-Making Tool Suite for Distributed Energy Resources Integration in Energy Markets

Energy markets are crucial for integrating Distributed Energy Resources (DER) into modern power grids. However, this integration presents challenges due to the inherent variability and decentralized nature of DERs, as well as poorly adapted regulatory environments. This paper proposes a medium-term decision-making approach based on a comprehensive suite of computational tools for integrating DERs into Colombian energy markets. The proposed framework consists of modular tools that are aligned with the operation of a Commercial Virtual Power Plant (CVPP). The tools aim to optimize participation in bilateral contracts and short-term energy markets. They use forecasting, uncertainty management, and decision-making modules to create an optimal portfolio of DER assets. The suite’s effectiveness and applicability are demonstrated and analyzed through its implementation with heterogeneous DER assets across various operational scenarios.

Developing a ‘fit for purpose’ approach to measuring methane emissions

Tackling methane emissions from fossil fuel operations represents one of the best near- and medium-term opportunities for limiting the effects of climate change. Over the last few years, independent methane studies have challenged the accuracy and completeness of publicly disclosed emissions estimates. To address this, new methane accounting and reporting frameworks have been developed. Central to these frameworks are key principles linked to measurement, monitoring, reporting, verification (MMRV) and reduction. Woodside has taken specific actions to measure and reduce its methane emissions and is developing a pathway to embed ongoing and sustainable measurements technologies in its operations. Previously, Woodside discussed the management and valuation of methane reductions, this paper will describe the approach taken to develop methane measurement plans including (i) the objective of measurement plans, (ii) measurement technology attributes and (iii) the identification of measurement technology use cases. It also overviews measurement techniques such as satellite, aerial, drone, handheld and continuous monitoring which can form part of a curated multi-scale approach to MMRV across a portfolio of assets.

Tourism supply and demand in the gateway communities of southeastern Utah (USA)

Although outdoor recreation and tourism drive the economies of many gateway and natural amenity regions (GNARs), community leaders in these areas often lack a clear understanding of how to strategically invest in resources in ways that lead to a balanced portfolio of assets that meets market demands. This research investigates the relationship between the supply of and demand for outdoor recreation and tourism in GNARs across southeastern Utah. We characterize supply assets using four asset classes: economic, environmental, infrastructural, and sociocultural. We quantify the demand for outdoor recreation and tourism using geotagged social media in gateway communities adjacent to national parks and other public lands. Our analysis revealed environmental assets (historic trails, viewpoints, proximity to national parks, and campsites specifically) are highly and significantly correlated with outdoor recreation and tourism demand. The findings can guide local, state, regional, and federal officials in strategically investing in tourism assets that align with market demands. For example, strategic investments across the study area in the development of viewpoints that showcase the region's spectacular red rock and desert landscapes, as well as campsites where visitors can base their explorations, are likely to see significant and positive returns in terms of visitation.

Comparative Study of the Equal-Weight Method and Hierarchical Risk Parity in Portfolio Construction

Purpose: Portfolio optimization is a process in which the capital is allocated among the portfolio assets such that the return is maximized while the risk is minimized. Portfolio construction and optimization has long been an active research area in finance. For the portfolios with highly correlated assets, the performance of traditional risk-based asset allocation methods such as, the mean-variance (MV) method is limited because quadratic optimizers require an inversion of the covariance matrix of the portfolio to distribute weight among the portfolio assets. Methods: A possible solution to the limitations of traditional risk-based asset allocation methods can be provided by a hierarchical clustering-based Machine Learning method because it uses hierarchical relationships between the covariance of assets in the portfolio to distribute the weight, and inversion of the covariance matrix is not required. A comparison of the performance of a simple non-optimization technique called the Equal-weight (EW) method to the two optimization methods, the Mean-variance method and the HRP method, which is a machine learning method, was conducted in this research. Results: It was found that in terms of cumulative returns, the equal-weight method has outperformed several more sophisticated optimization techniques, the mean-variance method, and the HRP method. For most of the period, the Sharpe ratio of the HRP method was observed to be similar to the mean-variance method and equal-weight method. Implications: This research supports the idea that HRP is a feasible method to construct portfolios with correlated assets because the performance of HRP is comparable to the performances of the traditional optimization method and the non-optimization method.

Research on the Optimal Strategy of Investment Portfolio Based on Markowitz Model

Nowadays, investment is becoming increasingly common. Under the globalization of the economy, investors are given more investment opportunities and choices. Investors need to select excellent assets and allocate the selected asset portfolio on weight during the investment process. The mean-variance model proposed by Markowitz plays an important guiding role in investment and risk management. This model can effectively evaluate investors portfolio risk and return decisions and significantly impact their decision-making choices. This study uses the data of the annual average return and variance from 11 risky assets and 1 risk-free asset in about 20 years to construct an investment portfolio in a fixed group based on the Markowitz Model. The study calculates the changes in the allocation of the maximum Sharpe ratio and the minimum variance portfolios under three different constraints and one condition with the addition of risk-free assets, respectively, and then analyzes changes in the outcome of data. The capital allocation lines are introduced to analyze the outcome of an investment portfolio with risk-free assets. Compared with the changes from three constraints, reasons are explained why these changes happen under three constraints. Then, the above limitations are taken as a premise, and the study proposes recommendations for the optimal investment portfolio selection for different investors according to the investment cycle, the preference of investors based on the situation of different investors, and market constraints. The study guides investors future investment decisions.

Stress test precision and bank competition

We study a banking sector in which banks choose their asset portfolios and, upon the public disclosure of stress test results, raise funding by promising investors a repayment. Competitive banks must gamble, choosing assets that are riskier the more precise is the stress test. Allocative efficiency, however, improves with precision. When risk taking is not too sensitive to the precision of information, maximal transparency maximizes both stability and surplus. In contrast, banks with market power select safer assets, and opacity maximizes stability, as well the surplus if the social cost of bank failure is significant.

Temporal Implicit Multimodal Networks for Investment and Risk Management

Many deep learning works on financial time-series forecasting focus on predicting future prices/returns of individual assets with numerical price-related information for trading, and hence propose models designed for univariate, single-task, and/or unimodal settings. Forecasting for investment and risk management involves multiple tasks in multivariate settings: forecasts of expected returns and risks of assets in portfolios, and correlations between these assets. As different sources/types of time-series influence future returns, risks, and correlations of assets in different ways, it is also important to capture time-series from different modalities. Hence, this article addresses financial time-series forecasting for investment and risk management in a multivariate, multitask, and multimodal setting. Financial time-series forecasting, however, is challenging due to the low signal-to-noise ratios typical in financial time-series, and as intra-series and inter-series relationships of assets evolve across time. To address these challenges, our proposed Temporal Implicit Multimodal Network (TIME) model learns implicit inter-series relationship networks between assets from multimodal financial time-series at multiple time-steps adaptively. TIME then uses dynamic network and temporal encoding modules to jointly capture such evolving relationships, multimodal financial time-series, and temporal representations. Our experiments show that TIME outperforms other state-of-the-art models on multiple forecasting tasks and investment and risk management applications.

Особливості фінансового посередництва в Україні

The emergence of financial intermediation in history was the result of the evolution of the process of distribution of functions in the field of financial services. Over time, this process became an important and independent branch of the economy. Modern financial intermediaries, forming the structure of the financial market, play a key role in ensuring effective interaction between those who have temporarily free funds and those who need them. They also help to significantly reduce the cost of financial transactions for businesses, as well as effectively spread and reduce risks among different investors. In addition, they help to increase the return on loan capital and improve portfolio asset management capabilities. Financial intermediaries are considered as financial institutions that specialize in collecting temporarily available funds from various market participants in order to provide financial services and meet the financial needs of participants in financial transactions, the main motive of which is to make a profit. The activity of financial intermediaries is important for the optimal functioning of the money market and, ultimately, for the development of a market economy. The main goal of their economic activity is to create the most favorable conditions for the successful functioning of the main participants of the money market. This means that financial intermediaries are directed to the outside world, to the real economy, in order to increase the efficiency of the subjects of this economy.

Portfolio optimisation of international real estate investment trusts market during COVID-19: A behavioural perspective

This paper employs the cumulative prospect theory to investigate how deviation from rational investor asset selection improves portfolio optimisation. Firstly, asset portfolios are constructed by utilising the cumulative prospect theory, which captures investors’ psychology and risk tolerance and is herein referred to as a behavioural portfolio (BF). Secondly, the cluster technique is also used to build behavioural-centred investment portfolios that capture all the relevant moment properties of the asset return distribution as well as investors’ psychological dynamics and risk appetite, herein called the cluster moment behavioural portfolio (CMBF). The constructed portfolios are optimised by copula and differential evolution techniques. The analysis of optimisation of the constructed portfolios indicates that for behavioural portfolios (BF), in all phases of our sample period, portfolios with higher behavioural scores outperformed those with lower behavioural scores. And in the cluster moment behavioural portfolio (CMBP), for the pre-COVID and the COVID phases, the portfolios with lower behavioural scores outperform those with higher behavioural scores; however, for the full sample phase, the portfolio with a higher behavioural score outperforms the portfolio with the lower behavioural scores. The optimisation results of all the constructed portfolios largely favour portfolios with higher behavioural scores over those with lower scores. The results offer investment suggestions to guide investors with varying risk tolerance levels and those who deviate from the rational investor on how they can enhance their portfolio optimisation.