Portfolio algorithm based on portfolio beta using genetic algorithm

  • Authors:

  • Kyong Joo Oh;Tae Yoon Kim;Sung-Hwan Min;Hyoung Yong Lee

  • Affiliations:

  • Department of Information and Industrial Engineering, Yonsei University, 134, Shinchon-Dong, Seodaemun-Gu, Seoul 120-749, South Korea;Department of Statistics, Keimyung University, Daegu 704-701, South Korea;Department of Business Administration, Hallym University, Gangwon-Do 200-702, South Korea;Department of Management Engineering, Korea Advanced Institute of Science and Technology, Seoul 130-722, South Korea

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2006

Quantified Score

Hi-index 12.07

Visualization

Abstract

The portfolio beta @b"p is quite an important coefficient in modern portfolio theory since it efficiently measures portfolio volatility relative to the benchmark index or the capital market. @b"p is usually employed for portfolio evaluation or prediction but scarcely for portfolio construction process. The main objective of this paper is to propose a portfolio algorithm that engages @b"p in its portfolio construction process and studies its strengths. Our portfolio algorithm termed as @b-G portfolio algorithm selects stocks based on their market capitalization and optimizes them in terms of the standard deviation of @b"p. The optimizing process or finding optimal weights is done by the genetic algorithm. Our major findings on @b-G portfolio algorithm are: (i) its performance depends on market volatility, i.e. it is expected to work well for a stable market whether it is bullish or bearish (ii) it tends to register outstanding performance for short-term applications.