计算机工程与应用 ›› 2013, Vol. 49 ›› Issue (6): 253-256.

• 工程与应用 • 上一篇    下一篇

基于捕食策略的粒子群算法求解投资组合问题

刘冬华,甘若迅,樊锁海,杨明华   

  1. 暨南大学 信息科学技术学院 数学系,广州 510632
  • 出版日期:2013-03-15 发布日期:2013-03-14

Particle Swarm Optimization based on Predatory Search for portfolio investment

LIU Donghua, GAN Ruoxun, FAN Suohai, YANG Minghua   

  1. Department of Mathematics, School of Information Science and Technology, Jinan University, Guangzhou 510632, China
  • Online:2013-03-15 Published:2013-03-14

摘要: 通过分析中国证券市场现实投资环境和实际特点,建立了一个考虑完整费用的证券投资组合模型。针对标准粒子群算法容易陷入局部最优和搜索精度不高的缺点,提出了基于捕食策略的粒子群算法,将其用于求解投资组合模型。捕食搜索策略可以通过调节限制级别来控制粒子群的搜索空间,从而平衡全局搜索和局部搜索。通过实例分析验证了算法的有效性。

关键词: 捕食搜索策略, 粒子群算法, 投资组合模型

Abstract: A portfolio investment model considering the complete trade expenses is built through analyzing the actual investment environment and characteristic. For the weakness that the standard Particle Swarm Optimization easily falls into local optimum and search precision faults, the Particle Swarm Optimization based on Predatory Search is raised to solve the portfolio investment model. Predatory search strategy can control the search space of the particle swarm through adjusting the level of restriction. Thereby, the global search and local search can be balanced. The algorithm is proven effective through an empirical analysis.

Key words: predatory search strategy, Particle Swarm Optimization(PSO), portfolio investment