We propose a dynamic decision support system (DDSS) capable of determining a near-optimal rule-combination for each time interval (window). The system provides Buy, Hold and Sell signals from which profitable trading decisions can be made. In DDSS, an intelligent rule selector(GARS) based on genetic algorithms and a sliding window scheme is developed. Experimental results on Taiwan stock exchange weighted stock index (TSEWSI) show that DDSS outperforms its static counterpart as well as the simple buy-and-hold strategy.

A novel evolutionary decision support system (EDSS) eflective for making profitable trading decisions in the stock market is presented. Genetic algorithms is incorporated with a sliding window scheme to effective& estimate the most profitable trading decision, namely, Buy, Hold, or Sell. Because of its data-driven nature and genetic change to the positive course, EDSS bypasses the complicated steps of network establishment and subsequent training, and it can directly deal with the problem of structural instability that plaques traditional rule-based systems. Empirical tests are conducted on the weighted price index of Taiwan stock market (TSE WSIJCompared to the buy-and-hold strategy, EDSS can achieve signiJicant projit gaim improvement.