A hybrid approach based on double roulette wheel selection and quadratic programming for cardinality constrained portfolio optimization

The portfolio optimization problem with cardinality constraint is usually solved by exact algorithms, heuristic algorithms, or combinations of them. We decompose the cardinality constraint mean-variance model, and determine the assets and proportions by double roulette wheel selection (DRWS) and quadratic programming (QP), respectively. Then the accuracy of the solution is improved by a local search after we obtain the preliminary solution by combining DRWS and QP. Experimental results show that the proposed algorithm achieves better accuracy and more efficiency than the algorithms in the literature. Therefore, we can see that the algorithm designed according to the characteristics of specific problems can improve the computational efficiency, but the algorithm needs to be adjusted for different problems.

Automated summary

The study focused on portfolio optimization with cardinality constraint, using double roulette wheel selection and quadratic programming to determine assets and proportions, with accuracy improved through local search. Experimental results demonstrated the algorithm's superior efficiency and accuracy compared to existing methods, showing that tailored algorithms can enhance computational efficiency but may require adjustments for different problems.