To address the issues of insufficient diversity and poor constraint-handling capability in the non-dominated sorting genetic algorithm Ⅱ (NSGA-Ⅱ) when solving portfolio optimization problems, a learning-based improved NSGA-Ⅱ algorithm (INSGA-Ⅱ) incorporating clustering and an adaptive feasibility repair strategy for multi-objective portfolio optimization was proposed. In the proposed algorithm, clustering learning was employed to enhance population diversity, while adaptive repair ensured that newly generated solutions were feasible, thereby improving the algorithm's diversity and convergence speed. Additionally, the populations after crossover and mutation were preserved separately and merged with the parent population to increase the selection pressure and quality of offspring generation. Experimental results demonstrate that the proposed algorithm exhibits superior search performance and stability, effectively solving multi-objective portfolio optimization problems.
HeQ Y, HeZ N, DuanS L,et al. Multi-objective interval portfolio optimization modeling and solving for margin trading[J]. Swarm and Evolutionary Computation,2022,75:101141.
[4]
ZhaoP X, GaoS, YangN C. Solving multi-objective portfolio optimization problem based on MOEA/D[C]//2020 12th International Conference on Advanced Computational Intelligence(ICACI). Dali,2020:30-37.
[5]
KaminJ H. Optimal portfolio revision with a proportional transaction cost[J]. Management Science,1975,21(11):1263-1271.
[6]
WangZ, LiuS Y. Multi-period mean-variance portfolio selection with fixed and proportional transaction costs[J]. Journal of Industrial & Management Optimization,2013,9(3):643-656.
MaYuan-yuan, LiuYan-ze, LiuCheng-long,et al. Chinese investors’ multi-perspective sentiment analysis and its role in stock market forecasting[J]. Journal of Northeastern University(Natural Science),2022,43(8):1201-1208,1216.
LiuShi-qi, SongJin-chun, YangBin. Comparison of three stage-wise superstructures of water network based on particle swarm optimization[J]. Journal of Northeastern University(Natural Science),2021,42(6):829-834.
[16]
XiangW L, LiY Z, HeR C,et al. Artificial bee colony algorithm with a pure crossover operation for binary optimization[J]. Computers & Industrial Engineering,2021,152:107011.
[17]
LiuS B, LinQ Z, LiJ Q,et al. A survey on learnable evolutionary algorithms for scalable multiobjective optimization[J]. IEEE Transactions on Evolutionary Computation,2023,27(6):1941-1961.
LinJia-li, JiangDa-zhi. Study on the portfolio problem based on differential evolution[J]. Journal of Shantou University(Natural Science Edition),2012,27(4):4-8.
SunYou-fa, LiXue-yan, LiuCai-yan,et al. Genetic algorithm based Markowitz portfolio model and stock price behavior[J]. Journal of Systems & Management,2012,21(4):546-551.
ChenGuo-fu, ChenXiao-shan, ZhangRui. A hybrid algorithm based on gravitational search and particle swarm for the portfolio optimization problem[J]. Operations Research and Management Science,2018,27(9):170-175.
ZhangYi. Research on improvement of artificial bee colony algorithm for portfolio problems[J]. Computer & Digital Engineering,2019,47(8):1869-1873,1894.
ZhengJi-ming, ZhengYong-jie, HuJi-tong,et al. Research on genetic algorithm for mean-CVaR portfolio model[J]. Science and Technology & Innovation,2020(20):12-14,18.
[28]
MaH P, ZhangY J, SunS Y,et al. A comprehensive survey on NSGA-Ⅱ for multi-objective optimization and applications[J]. Artificial Intelligence Review,2023,56(12):15217-15270.
[29]
Estrada-PadillaA, Gómez-SantillánC, Fraire-HuacujaH, et al. GRASP/Δ:an efficient algorithm for the multi-objective portfolio optimization problem[J]. Expert Systems with Applications,2023,211:118647.