Genetic algorithms in multi-stage asset allocation system

This paper presents a decision-making process that incorporates genetic algorithms into a multi-stage asset allocation system. The objective function is to maximize one's economic utility or end-of-period wealth. The performance of our system is demonstrated by optimizing the allocation of cash and various stocks to Shenzhen market of China. Experiments are conducted to compare performance of the portfolios optimized by different objective functions in terms of expected return and standard derivation.