Multi-objective approaches to portfolio optimization with market impact costs

Wang, Hongze1,2; Li, Xuerong3; Hong, Wenjing4; Tang, Ke4

2022-10-01

10.1007/s12293-022-00381-w

Memetic Computing   影响因子和分区

1865-9284

1865-9292

Market impact costs are important factors to portfolio management, which always lead to adverse price fluctuations in trading. As the practical trading volume becomes increasingly large, the Problem of Portfolio Optimization with Market Impact Costs (MICPOP) has become more important. Traditional MICPOPs involve seeking an optimal allocation of capital to a limited number of assets with respect to either additional constraints or a weighted sum of objectives (net return, investment risk). We suggest solving MICPOPs with Multi-Objective Evolutionary Algorithms (MOEAs). Specifically, we formulate MICPOPs as a bi-objective optimization problem. The advantages of MOEAs over state-of-the-art single objective approaches to MICPOPs will be shown through empirical studies. Our study has revealed that a well-known MOEA, namely Nondominated Sorting Genetic Algorithm II (NSGA-II), fails to provide satisfactory solution quality sometimes. Hence, a memetic MOEA for Portfolio Optimization with Market Impact costs (POMI-MOEA), which inherits the global search capability of NSGA-II while introducing a new local search operator, is proposed and evaluated in this paper. Comprehensive experimental studies on 11 portfolio cases have shown the superiority of POMI-MOEA over NSGA-II and other two MOEAs for MICPOPs.

Portfolio optimization Market impact cost Multi-objective optimization Evolutionary computation Memetic algorithm

SCI

英语

其他

National Natural Science Foundation of China[71901205]

Computer Science ; Operations Research & Management Science

Computer Science, Artificial Intelligence ; Operations Research & Management Science

WOS:000870949700001

SPRINGER HEIDELBERG

Web of Science

1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Acad Math & Syst Sci, Beijing 100190, Peoples R China
4.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Guangdong Prov Key Lab Brain Inspired Intelligent, Shenzhen 518055, Peoples R China

Wang, Hongze,Li, Xuerong,Hong, Wenjing,et al. Multi-objective approaches to portfolio optimization with market impact costs[J]. Memetic Computing,2022.

Wang, Hongze,Li, Xuerong,Hong, Wenjing,&Tang, Ke.(2022).Multi-objective approaches to portfolio optimization with market impact costs.Memetic Computing.

Wang, Hongze,et al."Multi-objective approaches to portfolio optimization with market impact costs".Memetic Computing (2022).