多目标差分进化算法在投资组合中的应用

Application of multi-objective DE algorithm in portfolio investment

针对多目标优化问题,提出一种改进的多目标差分进化算法.在基本的差分进化算法中引入了参数自适应调整操作和可行性规则操作.同时,在综合考虑交易费用的基础上建立多目标投资组合模型,并应用改进算法进行求解.结果表明,改进的多目标差分进化算法得到的多目标投资组合的收益率要高于其他算法得到的收益率.

An improved multi-objective differential evolution algorithm for multi-objective optimization problems was proposed.The adaptive adjustment of the parameters and operation rules are introduced in the basic differential evolution algorithm.A multi-objective optimization model of investment portfolio was built based on the transaction expenses and was resolved based on the improved algorithm.The results showed that the yield of the improved multi-objective differential evolution algorithm for multi-objective portfolio was more than other algorithms.