Trading Experimental Results

In this section we report some preliminary results. In order to compare our trading strategy with other existing
strategies we follow closely. In order to com pare our trading strategies with other existing strategies, we test them on one time period, namely for year 2000-2010. The corresponding training period is 1989-1998 (ten years). The comparison is made with. To facilitate the comparison, stock indexes from five countries are used in the paper.

Tables 1 lists the return from NT, TTP, GP (Genetic Programming) and twenty one practical trading strategies for selected countries in the test time period. The values listed are the investment returns as fraction (for example, 0.1778 in Table 1 means that the return is 17.78%) . For more details please refer to. The B&H refers to buy and hold strategy. We have the following observations based on the
results presented in Table 1.

1. TTP’s performance exceeds NT’s performance in most countries. This clearly indicates that the trend prediction is able to find the correct trend in some cases. The trading strategy considering the price trend does improve the trading performance.

2. As shown in Table 1 for the time period 2000-2010, TTP has the best performance for US and Singapore in comparison with GPs, i.e., GP 1 and 2, and the twenty one practical trading strategies. For UK, NT, which is slightly better than TTP, performs the best.

While all the twenty one practical trading strategies get negative or a slight positive return, TTP is able to produce significant positive returns for the time period 2000-2010. For Canada, GPs perform best, which is followed by B&H. TTP gives a slight positive return while most of the twenty one practical strategies get negative returns. For Taiwan, the GPs perform much better than all the other trading strategies. However TTP is able to exceed B&H and most of the twenty one practical strategies.