Investment portfolio optimization method based on multi-objective evolutionary algorithm

Abstract

The invention discloses an investment portfolio optimization method based on a multi-objective evolutionary algorithm, a medium and equipment. The method comprises the following steps: S1, generating neighbors; S2, initializing a calculation target of the population; S3, initializing two extreme points of the Pareto plane; S4, traversing the population; S5, generating a random number, and judging whether the random number is greater than a preset threshold, if so, executing S6, and if not, executing S7; S6, taking the population as a parent alternative pool; S7, taking the neighbors as a parent alternative pool; S8, determining a filial generation individual corresponding to the current individual to obtain a filial generation target; S9, updating the two extreme points according to the filial generation target; S10, calculating a corresponding Chebyshev value, and updating individuals and targets in the parent alternative pool; S11, determining a final target after iteration is finished; in the process of investment portfolio optimization through a multi-objective evolutionary algorithm, the convergence, diversity and global search ability of the algorithm can be improved.

Description

technical field [0001] The invention relates to the technical field of investment analysis, in particular to an investment combination optimization method based on a multi-objective evolutionary algorithm, a computer-readable storage medium and a computer device. Background technique [0002] Portfolio optimization involves two dimensions of return and risk; it can be modeled as a multi-objective optimization problem. [0003] In related technologies, decomposition-based objective evolutionary algorithms are often used to solve the multi-objective optimization problem; however, the frequency of such algorithms to generate better offspring in the later stage of iteration is very low. Moreover, the global search ability and the ability of parental self-adaptation are insufficient. Contents of the invention [0004] The present invention aims to solve one of the technical problems in the above-mentioned technologies at least to a certain extent. For this reason, an object o...

AI Technical Summary

Problems solved by technology

[0003] In related technologies, the decomposition-based objective evolution algorithm is often used to solve the multi-objective optimization problem; however, the frequency of this algorithm to produce better offspring in the later stage of iteration is very low

Moreover, the global search ability and the ability of parental self-adaptation are insufficient

Images