Decentralized Robust Portfolio Optimization Based on Cooperative-Competitive Multiagent Systems

Man-Fai Leung; Jun Wang; Duan Li

doi:10.1109/TCYB.2021.3088884

Decentralized Robust Portfolio Optimization Based on Cooperative-Competitive Multiagent Systems

Man-Fai Leung, Jun Wang^*, Duan Li

^*Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

26 Citations (Scopus)

Abstract

This article addresses decentralized robust portfolio optimization based on multiagent systems. Decentralized robust portfolio optimization is first formulated as two distributed minimax optimization problems in a Markowitz return-risk framework. Cooperative-competitive multiagent systems are developed and applied for solving the formulated problems. The multiagent systems are shown to be able to reach consensuses in the expected stock prices and convergence in investment allocations through both intergroup and intragroup interactions. Experimental results of the multiagent systems with stock data from four major markets are elaborated to substantiate the efficacy of multiagent systems for decentralized robust portfolio optimization.

Original language	English
Pages (from-to)	12785-12794
Journal	IEEE Transactions on Cybernetics
Volume	52
Issue number	12
Online published	14 Jul 2021
DOIs	https://doi.org/10.1109/TCYB.2021.3088884
Publication status	Published - Dec 2022

Research Keywords

Conditional value-at-risk (CVaR)
decentralized robust portfolio selection
distributed minimax optimization
Investment
Multi-agent systems
multiagent systems (MASs)
Optimization
Portfolios
Reactive power
Uncertainty
Urban areas

Access Output

10.1109/TCYB.2021.3088884

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{3f76f79d83664d019cb72c9f6d4d4bee,

title = "Decentralized Robust Portfolio Optimization Based on Cooperative-Competitive Multiagent Systems",

abstract = "This article addresses decentralized robust portfolio optimization based on multiagent systems. Decentralized robust portfolio optimization is first formulated as two distributed minimax optimization problems in a Markowitz return-risk framework. Cooperative-competitive multiagent systems are developed and applied for solving the formulated problems. The multiagent systems are shown to be able to reach consensuses in the expected stock prices and convergence in investment allocations through both intergroup and intragroup interactions. Experimental results of the multiagent systems with stock data from four major markets are elaborated to substantiate the efficacy of multiagent systems for decentralized robust portfolio optimization.",

keywords = "Conditional value-at-risk (CVaR), decentralized robust portfolio selection, distributed minimax optimization, Investment, Multi-agent systems, multiagent systems (MASs), Optimization, Portfolios, Reactive power, Uncertainty, Urban areas",

author = "Man-Fai Leung and Jun Wang and Duan Li",

year = "2022",

month = dec,

doi = "10.1109/TCYB.2021.3088884",

language = "English",

volume = "52",

pages = "12785--12794",

journal = "IEEE Transactions on Cybernetics",

issn = "2168-2267",

publisher = "IEEE",

number = "12",

}

TY - JOUR

T1 - Decentralized Robust Portfolio Optimization Based on Cooperative-Competitive Multiagent Systems

AU - Leung, Man-Fai

AU - Wang, Jun

AU - Li, Duan

PY - 2022/12

Y1 - 2022/12

N2 - This article addresses decentralized robust portfolio optimization based on multiagent systems. Decentralized robust portfolio optimization is first formulated as two distributed minimax optimization problems in a Markowitz return-risk framework. Cooperative-competitive multiagent systems are developed and applied for solving the formulated problems. The multiagent systems are shown to be able to reach consensuses in the expected stock prices and convergence in investment allocations through both intergroup and intragroup interactions. Experimental results of the multiagent systems with stock data from four major markets are elaborated to substantiate the efficacy of multiagent systems for decentralized robust portfolio optimization.

AB - This article addresses decentralized robust portfolio optimization based on multiagent systems. Decentralized robust portfolio optimization is first formulated as two distributed minimax optimization problems in a Markowitz return-risk framework. Cooperative-competitive multiagent systems are developed and applied for solving the formulated problems. The multiagent systems are shown to be able to reach consensuses in the expected stock prices and convergence in investment allocations through both intergroup and intragroup interactions. Experimental results of the multiagent systems with stock data from four major markets are elaborated to substantiate the efficacy of multiagent systems for decentralized robust portfolio optimization.

KW - Conditional value-at-risk (CVaR)

KW - decentralized robust portfolio selection

KW - distributed minimax optimization

KW - Investment

KW - Multi-agent systems

KW - multiagent systems (MASs)

KW - Optimization

KW - Portfolios

KW - Reactive power

KW - Uncertainty

KW - Urban areas

UR - http://www.scopus.com/inward/record.url?scp=85110873566&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85110873566&origin=recordpage

U2 - 10.1109/TCYB.2021.3088884

DO - 10.1109/TCYB.2021.3088884

M3 - RGC 21 - Publication in refereed journal

SN - 2168-2267

VL - 52

SP - 12785

EP - 12794

JO - IEEE Transactions on Cybernetics

JF - IEEE Transactions on Cybernetics

IS - 12

ER -

Decentralized Robust Portfolio Optimization Based on Cooperative-Competitive Multiagent Systems

Abstract

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: Risk-Potential Framework for Dynamic Portfolio Selection

GRF: Collaborative Neurodynamic Approaches to Portfolio Optimization

GRF: Analysis and Design of Multiscale Neurodynamic Systems with Their Applications for Robust Control, Data Processing, and Supervised Learning

Cite this

Decentralized Robust Portfolio Optimization Based on Cooperative-Competitive Multiagent Systems

Abstract

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: Risk-Potential Framework for Dynamic Portfolio Selection

GRF: Collaborative Neurodynamic Approaches to Portfolio Optimization

GRF: Analysis and Design of Multiscale Neurodynamic Systems with Their Applications for Robust Control, Data Processing, and Supervised Learning

Cite this