
Journal of Northeastern University(Natural Science) ›› 2025, Vol. 46 ›› Issue (9): 17-24.DOI: 10.12068/j.issn.1005-3026.2025.20249030
• Information & Control • Previous Articles Next Articles
Received:2024-05-26
Online:2025-09-15
Published:2025-12-03
Contact:
Zhu ZHU
CLC Number:
Zhu ZHU, Hang-yu LOU. Learning-Based NSGA-Ⅱ for Multi-objective Portfolio Optimization Problems[J]. Journal of Northeastern University(Natural Science), 2025, 46(9): 17-24.
| 序号 | 股票名称 | 股票代码 | 收益率/% | 价格/元 |
|---|---|---|---|---|
| 1 | 三一重工 | 600031 | 0.036 9 | 34.67 |
| 2 | 招商银行 | 600036 | 0.116 0 | 45.16 |
| 3 | 海天味业 | 603288 | 0.029 9 | 192.81 |
| 4 | 伊利股份 | 600887 | 0.024 9 | 42.27 |
| 5 | 美的电器 | 000333 | 0.017 9 | 93.07 |
| 6 | 海康威视 | 002415 | 0.047 0 | 49.41 |
| 7 | 良信股份 | 002706 | 0.034 3 | 26.91 |
| 8 | 爱尔眼科 | 300015 | 0.033 4 | 70.17 |
Table 1 Average weekly return and price of selected
| 序号 | 股票名称 | 股票代码 | 收益率/% | 价格/元 |
|---|---|---|---|---|
| 1 | 三一重工 | 600031 | 0.036 9 | 34.67 |
| 2 | 招商银行 | 600036 | 0.116 0 | 45.16 |
| 3 | 海天味业 | 603288 | 0.029 9 | 192.81 |
| 4 | 伊利股份 | 600887 | 0.024 9 | 42.27 |
| 5 | 美的电器 | 000333 | 0.017 9 | 93.07 |
| 6 | 海康威视 | 002415 | 0.047 0 | 49.41 |
| 7 | 良信股份 | 002706 | 0.034 3 | 26.91 |
| 8 | 爱尔眼科 | 300015 | 0.033 4 | 70.17 |
| 序号 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
|---|---|---|---|---|---|---|---|---|
| 1 | 21.27 | 11.43 | -1.52 | 5.03 | -5.00 | -9.71 | -15.30 | -7.59 |
| 2 | 11.43 | 8.42 | -0.17 | 2.92 | -3.82 | 2.08 | -11.01 | -0.01 |
| 3 | -1.52 | -0.17 | 6.02 | -5.91 | -0.78 | 6.14 | -7.04 | -2.74 |
| 4 | 5.03 | 2.92 | -5.91 | 20.69 | 2.24 | -20.49 | -1.51 | 11.84 |
| 5 | -5.00 | -3.82 | -0.78 | 2.24 | 16.74 | -13.13 | -1.99 | 2.15 |
| 6 | -9.71 | 2.08 | 6.14 | -20.49 | -13.13 | 67.84 | 4.03 | -15.69 |
| 7 | -15.30 | -11.01 | -7.04 | -1.51 | -1.99 | 4.03 | 29.06 | 2.10 |
| 8 | -7.59 | -0.01 | -2.74 | 11.84 | 2.15 | -15.69 | 2.10 | 44.14 |
Table 2 Covariance matrix of selected stocks
| 序号 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
|---|---|---|---|---|---|---|---|---|
| 1 | 21.27 | 11.43 | -1.52 | 5.03 | -5.00 | -9.71 | -15.30 | -7.59 |
| 2 | 11.43 | 8.42 | -0.17 | 2.92 | -3.82 | 2.08 | -11.01 | -0.01 |
| 3 | -1.52 | -0.17 | 6.02 | -5.91 | -0.78 | 6.14 | -7.04 | -2.74 |
| 4 | 5.03 | 2.92 | -5.91 | 20.69 | 2.24 | -20.49 | -1.51 | 11.84 |
| 5 | -5.00 | -3.82 | -0.78 | 2.24 | 16.74 | -13.13 | -1.99 | 2.15 |
| 6 | -9.71 | 2.08 | 6.14 | -20.49 | -13.13 | 67.84 | 4.03 | -15.69 |
| 7 | -15.30 | -11.01 | -7.04 | -1.51 | -1.99 | 4.03 | 29.06 | 2.10 |
| 8 | -7.59 | -0.01 | -2.74 | 11.84 | 2.15 | -15.69 | 2.10 | 44.14 |
| 算例 | IGD | HV | ||||||
|---|---|---|---|---|---|---|---|---|
| NSGA-Ⅱ | MOEA/D | NSGA-Ⅲ | INSGA-Ⅱ | NSGA-Ⅱ | MOEA/D | NSGA-Ⅲ | INSGA-Ⅱ | |
| ZDT1 | 2.00e-1 (1.12e-1) | 1.67e-1 (5.85e-2) | 6.30e-1 (2.42e-1) | 5.06e-3 (2.18e-4) | 5.50e-1 (6.57e-2) | 5.09e-1 (6.38e-2) | 1.66e-1 (1.30e-1) | 6.60e-1 (2.46e-4) |
| ZDT2 | 5.07e-1 (1.33e-1) | 3.92e-1 (1.74e-1) | 1.04e+0 (1.69e-1) | 5.13e-3 (2.86e-4) | 5.81e-2 (5.59e-2) | 1.34e-1 (6.92e-2) | 1.02e-1 (5.88e-2) | 3.27e-1 (3.66e-4) |
| ZDT3 | 1.79e-1 (1.03e-1) | 2.09e-1 (1.12e-1) | 4.24e-1 (2.02e-1) | 5.57e-2 (2.65e-4) | 6.49e-1 (8.87e-2) | 4.58e-1 (1.10e-1) | 3.61e-1 (1.31e-1) | 1.04e+0 (2.06e-4) |
| ZDT4 | 2.40e-1 (1.44e-1) | 4.80e-1 (2.13e-1) | 6.71e-1 (3.58e-1) | 4.98e-2 (3.13e-4) | 4.97e-1 (1.33e-1) | 2.16e-1 (1.46e-1) | 1.73e-1 (1.51e-1) | 6.60e-1 (8.67e-4) |
Table 3 Comparison of performance metrics of different algorithms
| 算例 | IGD | HV | ||||||
|---|---|---|---|---|---|---|---|---|
| NSGA-Ⅱ | MOEA/D | NSGA-Ⅲ | INSGA-Ⅱ | NSGA-Ⅱ | MOEA/D | NSGA-Ⅲ | INSGA-Ⅱ | |
| ZDT1 | 2.00e-1 (1.12e-1) | 1.67e-1 (5.85e-2) | 6.30e-1 (2.42e-1) | 5.06e-3 (2.18e-4) | 5.50e-1 (6.57e-2) | 5.09e-1 (6.38e-2) | 1.66e-1 (1.30e-1) | 6.60e-1 (2.46e-4) |
| ZDT2 | 5.07e-1 (1.33e-1) | 3.92e-1 (1.74e-1) | 1.04e+0 (1.69e-1) | 5.13e-3 (2.86e-4) | 5.81e-2 (5.59e-2) | 1.34e-1 (6.92e-2) | 1.02e-1 (5.88e-2) | 3.27e-1 (3.66e-4) |
| ZDT3 | 1.79e-1 (1.03e-1) | 2.09e-1 (1.12e-1) | 4.24e-1 (2.02e-1) | 5.57e-2 (2.65e-4) | 6.49e-1 (8.87e-2) | 4.58e-1 (1.10e-1) | 3.61e-1 (1.31e-1) | 1.04e+0 (2.06e-4) |
| ZDT4 | 2.40e-1 (1.44e-1) | 4.80e-1 (2.13e-1) | 6.71e-1 (3.58e-1) | 4.98e-2 (3.13e-4) | 4.97e-1 (1.33e-1) | 2.16e-1 (1.46e-1) | 1.73e-1 (1.51e-1) | 6.60e-1 (8.67e-4) |
| [1] | Markowitz H. Portfolio selection[J]. The Journal of Finance,1952,7(1):77-91. |
| [2] | Loke Z X, Goh S L, Kendall G,et al. Portfolio optimization problem:a taxonomic review of solution methodologies[J]. IEEE Access,2023,11:33100-33120. |
| [3] | He Q Y, He Z N, Duan S L,et al. Multi-objective interval portfolio optimization modeling and solving for margin trading[J]. Swarm and Evolutionary Computation,2022,75:101141. |
| [4] | Zhao P X, Gao S, Yang N 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] | Kamin J H. Optimal portfolio revision with a proportional transaction cost[J]. Management Science,1975,21(11):1263-1271. |
| [6] | Wang Z, Liu S Y. Multi-period mean-variance portfolio selection with fixed and proportional transaction costs[J]. Journal of Industrial & Management Optimization,2013,9(3):643-656. |
| [7] | 马源源,刘晏泽,刘呈隆,等. 中国投资者多角度舆情分析及其在股市预测中的作用[J]. 东北大学学报(自然科学版),2022,43(8):1201-1208,1216. |
| Ma Yuan-yuan, Liu Yan-ze, Liu Cheng-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. | |
| [8] | 李敏,黄敏,程智锋,等. 遗传算法在路径规划上的应用[J]. 计算机系统应用,2020,29(8):255-260. |
| Li Min, Huang Min, Cheng Zhi-feng,et al. Application of genetic algorithm in path planning[J]. Computer Systems & Applications,2020,29(8):255-260. | |
| [9] | Song Y J, Zhao G Y, Zhang B,et al. An enhanced distributed differential evolution algorithm for portfolio optimization problems[J]. Engineering Applications of Artificial Intelligence,2023,121:106004. |
| [10] | 陈婷婷,殷贺,江红莉,等. 基于天牛须搜索的粒子群优化算法求解投资组合问题[J]. 计算机系统应用,2019,28(2):171-176. |
| Chen Ting-ting, Yin He, Jiang Hong-li,et al. Particle swarm optimization algorithm based on beetle antennae search for solving portfolio problem[J]. Computer Systems & Applications,2019,28(2):171-176. | |
| [11] | 刘士琦,宋锦春,杨滨. 基于粒子群算法的3种分级水网络超结构比较[J]. 东北大学学报(自然科学版),2021,42(6):829-834. |
| Liu Shi-qi, Song Jin-chun, Yang Bin. 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. | |
| [12] | Xiang W L, Li Y Z, He R C,et al. Artificial bee colony algorithm with a pure crossover operation for binary optimization[J]. Computers & Industrial Engineering,2021,152:107011. |
| [13] | Liu S B, Lin Q Z, Li J Q,et al. A survey on learnable evolutionary algorithms for scalable multiobjective optimization[J]. IEEE Transactions on Evolutionary Computation,2023,27(6):1941-1961. |
| [14] | 林佳丽,姜大志. 基于差分演化算法的证券投资组合研究[J]. 汕头大学学报(自然科学版),2012,27(4):4-8. |
| Lin Jia-li, Jiang Da-zhi. Study on the portfolio problem based on differential evolution[J]. Journal of Shantou University(Natural Science Edition),2012,27(4):4-8. | |
| [15] | 孙有发,李雪岩,刘彩燕,等. 基于遗传算法的Markowitz策略模型与股票价格行为[J]. 系统管理学报,2012,21(4):546-551. |
| Sun You-fa, Li Xue-yan, Liu Cai-yan,et al. Genetic algorithm based Markowitz portfolio model and stock price behavior[J]. Journal of Systems & Management,2012,21(4):546-551. | |
| [16] | 陈国福,陈小山,张瑞. 基于引力搜索和粒子群混合优化算法的证券投资组合问题研究[J]. 运筹与管理,2018,27(9):170-175. |
| Chen Guo-fu, Chen Xiao-shan, Zhang Rui. 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. | |
| [17] | 张懿. 人工蜂群算法在投资组合问题中的优化应用[J]. 计算机与数字工程,2019,47(8):1869-1873,1894. |
| Zhang Yi. Research on improvement of artificial bee colony algorithm for portfolio problems[J]. Computer & Digital Engineering,2019,47(8):1869-1873,1894. | |
| [18] | 郑继明,郑永杰,胡济桐,等. 均值-CVaR投资组合模型的遗传算法求解研究[J]. 科技与创新,2020(20):12-14,18. |
| Zheng Ji-ming, Zheng Yong-jie, Hu Ji-tong,et al. Research on genetic algorithm for mean-CVaR portfolio model[J]. Science and Technology & Innovation,2020(20):12-14,18. | |
| [19] | Ma H P, Zhang Y J, Sun S Y,et al. A comprehensive survey on NSGA-Ⅱ for multi-objective optimization and applications[J]. Artificial Intelligence Review,2023,56(12):15217-15270. |
| [20] | Estrada-Padilla A, Gómez-Santillán C, Fraire-Huacuja H, et al. GRASP/Δ:an efficient algorithm for the multi-objective portfolio optimization problem[J]. Expert Systems with Applications,2023,211:118647. |
| [1] | Zhi-ao CAO, Chen-shuo MA. Charging and Discharging Scheduling for Electric Vehicles Based on Improved Multi-objective Chaotic Particle Swarm Optimization [J]. Journal of Northeastern University(Natural Science), 2025, 46(9): 1-8. |
| [2] | Shu-hong WANG, Hao-ran LI, Hong YIN, Fan GONG. Multi-objective Optimization of Fiber Foam Concrete Based on Response Surface Analysis [J]. Journal of Northeastern University(Natural Science), 2025, 46(6): 122-130. |
| [3] | Yang-jun WU, Zhen-ping LI, Hong-liang YAO, Sheng-dong HAN. Modeling and Optimization Design of Vehicle Powertrain System Considering Effect of Auxiliary Components [J]. Journal of Northeastern University(Natural Science), 2025, 46(4): 43-51. |
| [4] | LIU Xiao-xi, JIANG Hui-yan, LUO Min. Multi-constraint Optimal Puncture Path Planning Algorithm for Liver Cancer Ablation [J]. Journal of Northeastern University(Natural Science), 2023, 44(7): 922-930. |
| [5] | LI Zhan-shan, SONG Zhi-yang, HUA Yun-qiao. A Multi-modal Multi-objective Optimization Algorithm Based on Adaptive Search [J]. Journal of Northeastern University(Natural Science), 2023, 44(10): 1408-1415. |
| [6] | ZHANG Rui-you, WANG Chao-hui, CHEN Yong-qiang. Lyapunov Method for Solving Nonlinear Programming Problems Based on Control Ideas [J]. Journal of Northeastern University(Natural Science), 2021, 42(9): 1217-1226. |
| [7] | MA Lian-jie, ZUO Yu-chen, ZHOU Yun-guang, FU Hai-ling. Multi-objective Optimization of Tool Geometry Parameters in Turning Zirconia Ceramics [J]. Journal of Northeastern University Natural Science, 2020, 41(8): 1129-1134. |
| [8] | QI Xi-jing, TANG Liang, KANG Wei-xin, QIN Jiao-jiao. Multi-objective Decision-Making Method for Bridge Deck Maintenance Scheme for Highway [J]. Journal of Northeastern University Natural Science, 2020, 41(7): 1033-1040. |
| [9] | GONG Ya-dong, ZHANG Wei-jian, CAI Ming, ZHOU Xian-xin. Experimental Study on the Grinding Metamorphic Layer of Nickel-based Single Crystal Superalloy [J]. Journal of Northeastern University Natural Science, 2020, 41(6): 846-851. |
| [10] | TIAN Hui-xin, WANG Di, SHUAI Min-wei, LI Kun. Optimization of High-Speed Train Operation Plan for OD Passenger Flow [J]. Journal of Northeastern University Natural Science, 2020, 41(11): 1535-1542. |
| [11] | SONG Hang, WANG Ya-li, LIU Guo-qi, ZHANG Bin. Web Service Composition Optimization Method Based on Improved Multi-objective Artificial Bee Colony Algorithm [J]. Journal of Northeastern University Natural Science, 2019, 40(6): 777-782. |
| [12] | FAN Li , XIE Li-yang, ZHANG Na. Fatigue Robustness and Lightweight Design of Driving Axle Housing for Heavy Truck [J]. Journal of Northeastern University Natural Science, 2019, 40(3): 365-369. |
| [13] | GUAN Shou-ping, ZOU Li-fu, ZHANG Jing-jing. Interval Multi-objective Particle Swarm Optimization Algorithm and Its Application [J]. Journal of Northeastern University Natural Science, 2019, 40(11): 1521-1526. |
| [14] | QIN Xian-rong, ZHANG Qing, LIU Chao, XU Jian. Finite Element Model Updating of Tower Cranes Based on the Non-dominated Sorting Genetic Algorithm [J]. Journal of Northeastern University Natural Science, 2018, 39(7): 1017-1021. |
| [15] | WANG Da-zhi, SHI Tong-yu, LI Shuo, YU Lin-xin. A Multi-objective VPGA for Optimization Design of PMECD Based on Equivalent Magnetic Circuit Model [J]. Journal of Northeastern University Natural Science, 2017, 38(6): 772-777. |
| Viewed | ||||||
|
Full text |
|
|||||
|
Abstract |
|
|||||
