Using genetic algorithm to support clustering-based portfolio optimization by investor information

Donghyun Cheong, Young Min Kim, Hyun Woo Byun, Kyong Joo Oh, Tae Yoon Kim

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

A clustering-based portfolio optimization scheme that employs a genetic algorithm (GA) based on investor information for active portfolio management is presented. Whereas numerous studies have investigated trading behaviors, investor performance, and portfolio investment strategies, few works have developed investment strategies based on investor information. This study is conducted in two phases. First, a basket of portfolio (i.e., a collection of stocks held in individual portfolios) is developed through a cluster analysis of investor information. A GA is then employed to optimize the weights of the selected stocks. And the optimized portfolio is rebalanced to get excess return. It is concluded that the proposed multistage portfolio optimization scheme for active portfolio management generates superior results than previously proposed methods for the Korean stock market.

Original languageEnglish
Pages (from-to)593-602
Number of pages10
JournalApplied Soft Computing Journal
Volume61
DOIs
Publication statusPublished - 2017 Dec 1

Fingerprint

Genetic algorithms
Cluster analysis
Financial markets

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Cheong, Donghyun ; Kim, Young Min ; Byun, Hyun Woo ; Oh, Kyong Joo ; Kim, Tae Yoon. / Using genetic algorithm to support clustering-based portfolio optimization by investor information. In: Applied Soft Computing Journal. 2017 ; Vol. 61. pp. 593-602.
@article{2a04e3530d614c738f31b06d1b53ab61,
title = "Using genetic algorithm to support clustering-based portfolio optimization by investor information",
abstract = "A clustering-based portfolio optimization scheme that employs a genetic algorithm (GA) based on investor information for active portfolio management is presented. Whereas numerous studies have investigated trading behaviors, investor performance, and portfolio investment strategies, few works have developed investment strategies based on investor information. This study is conducted in two phases. First, a basket of portfolio (i.e., a collection of stocks held in individual portfolios) is developed through a cluster analysis of investor information. A GA is then employed to optimize the weights of the selected stocks. And the optimized portfolio is rebalanced to get excess return. It is concluded that the proposed multistage portfolio optimization scheme for active portfolio management generates superior results than previously proposed methods for the Korean stock market.",
author = "Donghyun Cheong and Kim, {Young Min} and Byun, {Hyun Woo} and Oh, {Kyong Joo} and Kim, {Tae Yoon}",
year = "2017",
month = "12",
day = "1",
doi = "10.1016/j.asoc.2017.08.042",
language = "English",
volume = "61",
pages = "593--602",
journal = "Applied Soft Computing",
issn = "1568-4946",
publisher = "Elsevier BV",

}

Using genetic algorithm to support clustering-based portfolio optimization by investor information. / Cheong, Donghyun; Kim, Young Min; Byun, Hyun Woo; Oh, Kyong Joo; Kim, Tae Yoon.

In: Applied Soft Computing Journal, Vol. 61, 01.12.2017, p. 593-602.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Using genetic algorithm to support clustering-based portfolio optimization by investor information

AU - Cheong, Donghyun

AU - Kim, Young Min

AU - Byun, Hyun Woo

AU - Oh, Kyong Joo

AU - Kim, Tae Yoon

PY - 2017/12/1

Y1 - 2017/12/1

N2 - A clustering-based portfolio optimization scheme that employs a genetic algorithm (GA) based on investor information for active portfolio management is presented. Whereas numerous studies have investigated trading behaviors, investor performance, and portfolio investment strategies, few works have developed investment strategies based on investor information. This study is conducted in two phases. First, a basket of portfolio (i.e., a collection of stocks held in individual portfolios) is developed through a cluster analysis of investor information. A GA is then employed to optimize the weights of the selected stocks. And the optimized portfolio is rebalanced to get excess return. It is concluded that the proposed multistage portfolio optimization scheme for active portfolio management generates superior results than previously proposed methods for the Korean stock market.

AB - A clustering-based portfolio optimization scheme that employs a genetic algorithm (GA) based on investor information for active portfolio management is presented. Whereas numerous studies have investigated trading behaviors, investor performance, and portfolio investment strategies, few works have developed investment strategies based on investor information. This study is conducted in two phases. First, a basket of portfolio (i.e., a collection of stocks held in individual portfolios) is developed through a cluster analysis of investor information. A GA is then employed to optimize the weights of the selected stocks. And the optimized portfolio is rebalanced to get excess return. It is concluded that the proposed multistage portfolio optimization scheme for active portfolio management generates superior results than previously proposed methods for the Korean stock market.

UR - http://www.scopus.com/inward/record.url?scp=85028936428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028936428&partnerID=8YFLogxK

U2 - 10.1016/j.asoc.2017.08.042

DO - 10.1016/j.asoc.2017.08.042

M3 - Article

AN - SCOPUS:85028936428

VL - 61

SP - 593

EP - 602

JO - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

ER -