SOFT COMPUTING AND HYBRID AI APPROACHES TO INTELLIGENT PREDICTION

Soft computing is considered as a good candidate to deal with imprecise and uncertain problems in stock market forecasting. However, soft computing systems have limitations, there is a demand for complex systems combining various approaches. Generally, AI systems can be combined with other AI systems or with mathematical tools. Hybrid systems consisting of a neural network added to genetic algorithms, fuzzy or rough set systems, have become a standard approach. In this paper, general observations about hybrid rough Neural, fuzzy neural and genetic neural are presented. Then I investigate a comparison between the performances of these hybrid models in predicting the trend for stock market because, the nature of the stock market prediction problem requires combining several computing techniques synergistically rather than exclusively