Quantum beetle antennae search: a novel technique for the constrained portfolio optimization problem
Quantum beetle antennae search: a novel technique for the constrained portfolio optimization problem
复制标题
DOI：
10.1007/s11432-020-2894-9
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
A. Khan;Xinwei Cao;Shuai Li;B. Hu;V. Katsikis
中科院分区：
文献类型：
--
作者：
A. Khan;Xinwei Cao;Shuai Li;B. Hu;V. Katsikis
在本文中，我们制定了量子甲虫天线搜索（QBAS），一种元启发式优化算法，以及甲虫天线搜索（BAS）的变体。我们将其应用于投资组合选择，这是一个众所周知的金融问题。量子计算在科学界越来越受欢迎，因为它在效率和速度上超越了传统计算。所有传统的计算算法都不能直接与量子计算机兼容，因此我们需要利用量子力学原理来制定它们的变体。在投资组合优化问题中，我们需要找到一组最优股票，使其最小化风险因素并最大化投资组合的平均回报。据我们所知，目前还没有应用量子元启发式算法来解决这个问题。我们将 QBAS 应用于现实世界的股票市场数据，并将结果与其他元启发式优化算法进行比较。获得的结果表明，QBAS 优于粒子群优化（PSO）和遗传算法（GA）等群体算法。
In this paper, we have formulated quantum beetle antennae search (QBAS), a meta-heuristic optimization algorithm, and a variant of beetle antennae search (BAS). We apply it to portfolio selection, a well-known finance problem. Quantum computing is gaining immense popularity among the scientific community as it outsmarts the conventional computing in efficiency and speed. All the traditional computing algorithms are not directly compatible with quantum computers, for that we need to formulate their variants using the principles of quantum mechanics. In the portfolio optimization problem, we need to find the set of optimal stock such that it minimizes the risk factor and maximizes the mean-return of the portfolio. To the best of our knowledge, no quantum meta-heuristic algorithm has been applied to address this problem yet. We apply QBAS on real-world stock market data and compare the results with other meta-heuristic optimization algorithms. The results obtained show that the QBAS outperforms swarm algorithms such as the particle swarm optimization (PSO) and the genetic algorithm (GA).