Enhanced QPSO driven by swarm cooperative evolution and its applications in portfolio optimization

Being a simple and popular method grounded in swarm evolution, Quantum-behaved particle swarm optimization (QPSO) has been extensively implemented to seek the optimal solution of various practical cases. Nevertheless, while managing intricate multimodal problems, the original QPSO algorithm renders the algorithm susceptible to premature convergence, characterized by slow iteration speed and suboptimal searching precision. To deal with these disadvantages, this paper puts forward an enhanced QPSO driven by swarm cooperative evolution (SCQPSO). In the SCQPSO algorithm, a binary swarm cooperative evolution strategy is designed to enhance QPSO’s convergence speed and optimization precision. Additionally, some improvement measures including Halton sequence initialization of individual locations, maintenance of population diversity, and mutation strategy for out-of-bounds particles, are also adopted to facilitate prevention of premature convergence and assist the algorithm in overcoming local optimality. Then, compared results obtained by SCQPSO and six improved intelligent approaches on CEC 2017 cases indicate that SCQPSO offers highly competitive solutions when solving complex multimodal problems. Further, the exceptional capability of SCQPSO in addressing two portfolio optimization issues demonstrates its outstanding global search performance.