摘要
人工蜂群算法是一种人工智能算法,被广泛地应用于求解各类优化问题,都达到了较为理想的结果。本文主要利用改进的人工蜂群算法研究了经典的证券投资组合优化模型,首先过基于公司基本面设计的计分函数挑选出股票,然后利用人工蜂群算法优化被挑选股票的权重。将人工蜂群算法与差分进化算法、粒子群算法等经典优化算法进行性能比较,从而验证算法的有效性以及所得模型的实用性。后改进MATLAB仿真实验,结果表明,在一定的风险水平下,改进的人工蜂群算法构建的投资组合与上述对比算法构建的投资组合以及指数型投资组合相比,获得的收益更高。
Artificial Bee Colony Algorithm is one of the artificial-intelligence algorithms, which has already applied into various optimization problems widely and has got excellent result. The objective of this paper is to create an optimum portfolio using ABC algorithm. The algorithm selects stocks on the basis of the scoring function designed on company fundamentals, and then assigns optimum weights to the selected stocks by ABC algorithm. Comparing the ABC algorithm with differential evolution algorithm and particle swarm optimization algorithm, it is verified that the validity of the algorithm and the practicality of the model. The results have been demonstrated by developing a MATLAB code to implement the algorithm shows that the portfolio which is constructed by the proposed ABC algorithm gets more profits than others, including the exponential portfolio.
出处
《计算机科学与应用》
2017年第11期1135-1145,共11页
Computer Science and Application
