Abstract: Aiming at the disadvantages of artificial fish swarm algorithm, such as low precision and easily falling into local optimum, combining the idea of gravity algorithm and teaching optimization, a two-population fish swarm search algorithm is proposed. Cross-thinking is adopted to optimize the results obtained by the two populations and avoid the local optimization. Metropoils criterion of simulated annealing is added to the standard function verifies the algorithm, and the results show that the two-population fish swarm algorithm is better than the traditional artificial fish swarm algorithm and the known literature algorithm. Based on the known literature, a distributed portfolio model is proposed, in which the design algorithm is applied to solve the distributed portfolio model, and verifies the effectiveness of the algorithm in solving the discrete portfolio optimization problem.

Key words: two-population fish swarm algorithm, gravitational search, teaching optimization, distributed portfolio problems