Ghanbari Hossein, Tavakoli Sina, Shabani Mostafa, Mohammadi Emran, Sadjadi Seyed Jafar, Kumar Ronald Ravinesh
Department of Industrial Engineering, Iran University of Science and Technology, Tehran, Iran.
Department of Economics and Finance, The Business School, RMIT University, Saigon South Campus, Ho Chi Minh City, Vietnam.
PLoS One. 2025 Jul 21;20(7):e0325973. doi: 10.1371/journal.pone.0325973. eCollection 2025.
In an increasingly diverse investment landscape, the cryptocurrency market has emerged as a compelling option, offering the potential for high returns, diversification opportunities, and significant liquidity. However, the inherent volatility and regulatory uncertainties of this market present substantial risks, underscoring the need for a well-structured investment strategy. Among the various strategies available, portfolio optimization has become a dynamic and evolving area of focus in finance. Despite advancements in financial modeling, traditional portfolio optimization models often fall short, as uncertainty remains a fundamental characteristic of capital markets. To address this challenge, this paper integrates credibility theory with the Conditional Value-at-Risk (CVaR) framework, harnessing their combined strengths in modeling downside risk and managing uncertainty. Nevertheless, relying solely on this model may not be sufficient for achieving optimal investment outcomes, as portfolio optimization models often neglect the crucial step of selecting high-quality assets. This highlights the essential need for a robust pre-selection process. To tackle this issue, this paper introduces a novel pre-selection framework based on Multi-Attribute Decision Making (MADM) methods. Acknowledging that different MADM approaches can yield varying results-which creates uncertainty regarding the most reliable method-this research proposes a systematic framework for asset evaluation. By considering these factors, this paper proposes a two-stage framework for enhancing cryptocurrency portfolio performance. Stage 1, involves establishing comprehensive performance criteria for cryptocurrencies and employing a novel method for asset pre-selection. Stage 2 focuses on optimizing the selected assets using a credibilistic CVaR model, while considering practical constraints from real-world investment scenarios. The results of this two-stage framework demonstrate its effectiveness in constructing well-diversified and efficient portfolios, addressing both the challenges of asset pre-selection and the complexities associated with uncertainty. By integrating these methodologies, investors can navigate the risks associated with cryptocurrency investments more effectively while maximizing potential returns.
在日益多样化的投资格局中，加密货币市场已成为一个极具吸引力的选择，它提供了高回报、多元化机会以及显著流动性的潜力。然而，该市场固有的波动性和监管不确定性带来了巨大风险，凸显了制定结构合理的投资策略的必要性。在众多可用策略中，投资组合优化已成为金融领域一个动态且不断发展的重点领域。尽管金融建模取得了进展，但传统的投资组合优化模型往往存在不足，因为不确定性仍然是资本市场的一个基本特征。为应对这一挑战，本文将可信性理论与条件风险价值（CVaR）框架相结合，利用它们在下行风险建模和不确定性管理方面的综合优势。然而，仅依靠该模型可能不足以实现最佳投资结果，因为投资组合优化模型往往忽略了选择优质资产这一关键步骤。这凸显了强大的预选过程的迫切需求。为解决这个问题，本文引入了一种基于多属性决策（MADM）方法的新型预选框架。鉴于不同的MADM方法可能产生不同的结果——这就产生了关于最可靠方法的不确定性——本研究提出了一个系统的资产评估框架。考虑到这些因素，本文提出了一个两阶段框架来提升加密货币投资组合的绩效。第一阶段，涉及为加密货币建立全面的绩效标准，并采用一种新型的资产预选方法。第二阶段专注于使用可信性CVaR模型优化所选资产，同时考虑现实世界投资场景中的实际约束。这个两阶段框架的结果证明了它在构建多元化且高效的投资组合方面的有效性，既解决了资产预选的挑战，又应对了与不确定性相关的复杂性。通过整合这些方法，投资者可以更有效地应对与加密货币投资相关的风险，同时最大化潜在回报。
