Stock valuation and dynamic asset allocation with genetic algorithm and cubic spline

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 donpsilat 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. The cubic spline provides a powerful numerical approximation over the shape of asset allocation curve. From our experiments, this model could earn better investment returns than the return of TSEC Taiwan 50 index.