Scholarlink

<p>In the ever-changing landscape of equity markets, investors continuously seek strategies that effectively balance risk and return. This growing demand underscores the importance of resilient, flexible, and data-driven approaches to portfolio construction and risk management. This study proposes a novel PCA-KMeans stratified selection technique to enhance the asset selection process for optimization solvers, including Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), and Sequential Least Squares Programming (SLSQP). The PCA-KMeans stratified selection technique is a multi-objective stock screening and diversification pipeline that evaluates asset quality using composite scores and ensures diversification by applying K-Means clustering. By improving the quality of selected assets, the technique significantly improves portfolio performance across six major stock markets: the US, the UK, India, China, Taiwan, and Vietnam. The optimized portfolios offer impressive returns at risk levels below 15%, aligning well with the preferences of conservative investors. Notably, the Sharpe ratio achieved in some cases reaches up to 4.0, demonstrating the effectiveness of the proposed method in delivering high risk-adjusted returns.</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

Portfolio optimization in stock investment

  • 期刊论文

  • 发表日期：

    2026年2月17日

查看全文
  • Tram Thi Hoai Vo,
  • Pai-Chou Wang,
  • Tien-Thinh Nguyen

摘要

In the ever-changing landscape of equity markets, investors continuously seek strategies that effectively balance risk and return. This growing demand underscores the importance of resilient, flexible, and data-driven approaches to portfolio construction and risk management. This study proposes a novel PCA-KMeans stratified selection technique to enhance the asset selection process for optimization solvers, including Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), and Sequential Least Squares Programming (SLSQP). The PCA-KMeans stratified selection technique is a multi-objective stock screening and diversification pipeline that evaluates asset quality using composite scores and ensures diversification by applying K-Means clustering. By improving the quality of selected assets, the technique significantly improves portfolio performance across six major stock markets: the US, the UK, India, China, Taiwan, and Vietnam. The optimized portfolios offer impressive returns at risk levels below 15%, aligning well with the preferences of conservative investors. Notably, the Sharpe ratio achieved in some cases reaches up to 4.0, demonstrating the effectiveness of the proposed method in delivering high risk-adjusted returns.