| Summary: | 碩士 === 國立臺灣科技大學 === 資訊管理系 === 97 === Investors have long faced the dilemma between higher returns and higher risks while trading in the stock market. To solve this problem, there are lots of researches emphasize on diversification of risks by constructing portfolios.
This research focuses on applying the artificial intelligence tool to the portfolio selection strategy and spread trading, using the data of Taiwan 50 during April 2005 to March 2008. We use the new stock selection index to construct a portfolio to do the trading empirical study and find out the below conclusion:
1. In the aspect of stock return forecasting ability, using the Grey Fourier model gets better performance than using GM(1,1)model; and in the aspect of return volatility, using GM(1,1) gets better performance than GARCH(1,1) model.
2. According to the concept that the stock fluctuation will be effected by its direction of return and volatility, this research constructs a new stock selection index. We can construct a portfolio which has better performance than Taiwan 50 by this index.
3. In the timing strategy, using three signals of the same direction of return on investment can estimate the outcome of the next trading more correctly than using two signals.
4. In the period of this research, taking action or not on the timing strategy doesn’t make significant difference when we estimate there will be negative value of its return on investment.
5. When applying the portfolio constructed by the ranking first 26 stocks on the timing strategy of using three signals of positive return on investment value shows the best outcome.
|
|---|
