Enterprise Portfolio Optimization Based on Particle Swarm Optimization and Quantum Approximate Optimization Algorithm

With the development of intelligent algorithms, new challenges have emerged in the financial field in optimizing the investment portfolio. In view of the current problems existing in portfolio optimization, the particle swarm algorithm (Particle Swarm Optimization, PSO) and quantum approximation optimization algorithm (Quantum Approximate Optimization Algorithm, QAOA) of the initial population Qanta coding is improved, and a hybrid algorithm suitable for solving enterprise portfolio optimization problems is proposed. The results found that the average performance of this method is below 0.06, which is better compared with the comparison algorithm. At the same time, with the increase of the risk level, the maximum, minimum and average increase of the yield are $10.99 \%, 19.80 \%$ and 7.98% respectively, stabilizing. The results show that the research algorithm is effective in solving the enterprise portfolio optimization problem, has better optimization ability in practical application, and can provide reference for enterprise investors to make investment decisions.