Portfolio algorithm based on portfolio beta using genetic algorithm

Kyong Joo Oh

doi:10.1016/j.eswa.2005.10.010

2006-04-01

PRE

Kyong Joo Oh

Tae Yoon Kim

Sung-Hwan Min

DOI：10.1016/j.eswa.2005.10.010

原文链接

原文求助

摘要

En 中文

The portfolio beta beta(p) is quite an important coefficient in modem portfolio theory since it efficiently measures portfolio volatility relative to the benchmark index or the capital market. beta(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 beta(p) in its portfolio construction process and studies its strengths. Our portfolio algorithm termed as beta-G portfolio algorithm selects stocks based on their market capitalization and optimizes them in terms of the standard deviation of beta(p). The optimizing process or finding optimal weights is done by the genetic algorithm. Our major findings on beta-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. (c) 2005 Elsevier Ltd. All rights reserved.

Keyword:

portfolio

beta

genetic algorithm