Markowitz's Portfolio Selections Based On Genetic Algorithm

With the great improvement of China's economic strength, a lot of investment projects have strong development potential. In the face of numerous investment instruments, how the investors choose the optimal portfolio investment is more and more significant. Markowitz's Portfolio Selections Model, Mean-Variance Model, is the base of modern portfolio selections. However, in the practice, this model is limited.Therefore, the no-risk asset is added based on the actual situations of China's securities market. And the profit-risk bi-objectives nonlinear programming model is built up on the basis of the greatest expected profits and the minimal risk of uncertainty. How to solve this model is quite complex and has been focused recently. Genetic algorithm is a new calculation method including natural genetics and computer science, which provides a common framework to solve the nonlinear, multi-model and multi-objective optimization problem. Thus, the genetic algorithm is designed to settle the profit-risk Bi-objectives nonlinear programming model. Meanwhile, by the use of the penalty function, the model is solved in the MATLAB by programming.Insurance investment is an important mainstay for insurance industry to survive and develop. The development of insurance investment will influence the insurer's own solvency and persistent business stability. Under the recent economic circumstances, how to develop the insurance investment and increase the benefits is needed to be investigated urgently. This paper uses China's insurance investment as the object of empirical research and gives the effective insurance investment portfolio. The result shows that this method is scientific and reasonable, and can supply the investors with the effective theoretical guidance.