Scholarlink

<p>Portfolio optimization, which aims to distribute assets in a way that optimizes returns while minimizing risk, is still a crucial issue in financial decision-making. The Directional Selective Lévy Flight Beagle-Inspired Optimization method (DSLF-BIOA), a unique nature-inspired method, is presented in this paper to address practical portfolio optimization issues. To efficiently strike a balance between discovery and exploitation, DSLF-BIOA combines Lévy flight-based exploration with directional movement toward viable solutions. Particle Swarm Optimization (PSO) and Differential Evolution (DE), two well-known metaheuristic algorithms, are used to compare the suggested approach. From a chosen basket of the best-performing NIFTY equities, all algorithms seek to optimize the Sharpe Ratio while preserving diversity among at least five stocks. Constraint handling, risk-return analysis, and historical data analysis are all part of the experimental setting. According to comparative findings, DSLF-BIOA produces competitive returns and well-diversified portfolios with reduced risk while preserving a steady convergence profile. For reproducibility, CSV-based result reporting and visualization are supplied. The study emphasizes how DSLF-BIOA can be used to create sensible investment plans in erratic markets.</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

A Novel Directional Selective Lévy Flight-Based Beagle Optimization for Diversified Portfolio Selection

  • 期刊论文

  • 发表日期：

    2026年4月9日

查看全文
  • Samindar Jalandar Vibhute,
  • Chetan Shripal Arage

摘要

Portfolio optimization, which aims to distribute assets in a way that optimizes returns while minimizing risk, is still a crucial issue in financial decision-making. The Directional Selective Lévy Flight Beagle-Inspired Optimization method (DSLF-BIOA), a unique nature-inspired method, is presented in this paper to address practical portfolio optimization issues. To efficiently strike a balance between discovery and exploitation, DSLF-BIOA combines Lévy flight-based exploration with directional movement toward viable solutions. Particle Swarm Optimization (PSO) and Differential Evolution (DE), two well-known metaheuristic algorithms, are used to compare the suggested approach. From a chosen basket of the best-performing NIFTY equities, all algorithms seek to optimize the Sharpe Ratio while preserving diversity among at least five stocks. Constraint handling, risk-return analysis, and historical data analysis are all part of the experimental setting. According to comparative findings, DSLF-BIOA produces competitive returns and well-diversified portfolios with reduced risk while preserving a steady convergence profile. For reproducibility, CSV-based result reporting and visualization are supplied. The study emphasizes how DSLF-BIOA can be used to create sensible investment plans in erratic markets.