股票组合的选取以及对风险的度量在投资过程中极为 重要. 基于熵模型和CVaR风险度量方法, 文章提出了一种新的多目 标投资组合优化模型, 并利用模糊集理论和粒子群算法对模型进行求解. 同时, 通过深圳综合指数、中小板综合指数和上证180指数的实际股票数据进行实证分析, 结果表明与其他经典投资组合模型相比, 文章所提出的模型在Sharpe比率、平均绝对偏差比、调整后的偏度Sharpe比率等评估指标中表现得更好, 同时具有更高的稳定性. 文章所得结论为丰富现有的投资组合理论基础做出了一定的贡献.

The selection of stock portfolio and the measurement of risk are of great significance in investments. Based on the entropy model and the CVaR function, this paper proposes a new multi-objective portfolio optimization model. In addition, a combination of fuzzy set theory and particle swarm optimization algorithm is employed to solve the model. By using the data of stocks included by the Shenzhen Composite index, SME composite index, and SSE 180 Index, a comparative empirical analysis is carried out. Five assessment metrics, including but not limited to Sharpe Ratio, Mean Absolute Deviation Ratio, Adjusted Skewness Sharpe Ratio and Farinelli and Tibiletti Ratio are used to evaluate the performane of the model. The results show that the proposed model has better performance in both utility and stability compared to other existing models, namely, Mean-Variance-Skewness Model, Entropy-Entropy Model and Entropy-Entropy-Skewness Model. The conclusion of this paper has made some contribution to enrich the current knowledge of portfolio theory.