An adaptive bird swarm algorithm with irregular random flight and its application.

• A scheme for the change of the flight behavior period in the bird swarm is proposed. • An adaptive strategy of the bird swarm is given to identify the producers and scroungers. • The local convergence of the improved algorithm is proved. • The detailed method for solving asset selection problem using AI-BSA is provided. The bird swarm algorithm (BSA) is a very important bionic intelligence algorithm which can be used to solve many optimization problems. The main idea of this paper is to increase the effectiveness of BSA by improving the flight behaviour. This paper provides an adaptive bird swarm algorithm with the irregular random flight (AI-BSA) for solving the portfolio optimization problems with cardinality constraints. We prove the local convergence of AI-BSA under mild conditions and verify the effectiveness of AI-BSA via some numerical tests. Moreover, we give a detailed process for solving the cardinality constrained portfolio optimization problem by using AI-BSA and provide a numerical example to compare with both the bird swarm algorithm and particle swarm optimization. [ABSTRACT FROM AUTHOR]