Research on Securities Portfolio Model Based on Genetic Optimization Neural Network

Portfolio is an investment management concept different from individual asset management. This consideration leads to interesting result, that is, investors should buy a variety of securities at the same time instead one kind for diversified investment. Aiming limitations BPNN (BP neural network) in traditional artificial network and its shortcomings such as many iterations, low convergence accuracy, poor generalization, portfolio method based on GA_BPNN (Genetic Optimization Neural Network) was proposed. The setting GA (genetic algorithm) parameters are discussed detail, implementation steps genetic BP algorithm described. results show evaluation indexes prediction model obviously better than those comparison model, with coincidence rate 77.96% average absolute error 12.451. combination can effectively solve this problem. simulation optimizing optimization scheme quadratic programming method, more correct, efficient, practical.