Scholarlink

<p>This paper proposes a three-step top-down methodology for optimizing an investment portfolio. The first step focuses on identifying the best-performing exchange-traded funds from an extensive asset list for each phase of the market cycle. The second step (macro allocation) builds on the first by promoting allocation through the maximization of risk-adjusted returns under uncertainty, utilizing a probabilistic framework. The third step (micro allocation) employs a hidden Markov model approach to characterize the dynamics of asset returns, allowing the application of a mean-variance framework to optimize allocation. The framework also proposes the application of a Generative Adversarial Network to improve risk assessment without prior assumptions about data probabilistic distribution. Experimental results have demonstrated promising risk-adjusted returns, outperforming the S&amp;P 500 benchmark. Additionally, the Micro Allocation approach has proven effective in refining asset weights in stock indices, achieving good performance when applied to IBOVESPA (Brazilian equities index). In particular, all proposed steps individually contribute to improving portfolio performance and can be used together or separately. The framework is sufficiently generic to accommodate various time series forecasting methods with different levels of complexity, as well as to enable integration with fundamentalist approaches.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Quantitative portfolio optimization framework with market regimes classification, probabilistic time series forecasting, and hidden Markov models

  • 期刊论文

  • 发表日期：

    2025年8月13日

查看全文
  • Marcus Oliveira,
  • Gilson Costa

摘要

This paper proposes a three-step top-down methodology for optimizing an investment portfolio. The first step focuses on identifying the best-performing exchange-traded funds from an extensive asset list for each phase of the market cycle. The second step (macro allocation) builds on the first by promoting allocation through the maximization of risk-adjusted returns under uncertainty, utilizing a probabilistic framework. The third step (micro allocation) employs a hidden Markov model approach to characterize the dynamics of asset returns, allowing the application of a mean-variance framework to optimize allocation. The framework also proposes the application of a Generative Adversarial Network to improve risk assessment without prior assumptions about data probabilistic distribution. Experimental results have demonstrated promising risk-adjusted returns, outperforming the S&P 500 benchmark. Additionally, the Micro Allocation approach has proven effective in refining asset weights in stock indices, achieving good performance when applied to IBOVESPA (Brazilian equities index). In particular, all proposed steps individually contribute to improving portfolio performance and can be used together or separately. The framework is sufficiently generic to accommodate various time series forecasting methods with different levels of complexity, as well as to enable integration with fundamentalist approaches.