GA-based Stock Valuation and Dynamic Asset Allocation with Market Pattern consideration

• Main Authors: Chih-Shu Shih, 施志樹
• Other Authors: Ping-Chen Lin
• Format: Others
• Language: zh-TW
• Published: 2008
• Online Access: http://ndltd.ncl.edu.tw/handle/37416043053136419097

碩士 === 國立高雄應用科技大學 === 金融資訊研究所 === 96 === The purpose of stock valuation for investors is to find the true value of stock based on financial analysis and to further earn excess return. However, the better asset allocation and suited trading moment are not considered in the traditional valuation models. Both of them play important roles to improve investment return for investors. Market pattern means the tendency of the stock market. We often know the formation of the market pattern, but we often don’t know what to take a position. In this article, we propose a stock valuation model with asset allocation strategy which could provide a suitable trading strategy for each market pattern. In this model, genetic algorithm is used to optimize the fair stock price range, anticipative rate of investment, and trading moment. From our experiments, although this model could not earn better investment returns than buy and hold strategy, it could earn better investment returns than the return of TAIEX.