Fuzzy neural systems for decision making

A stock selection strategy based on an artificial fuzzy neural system is described from a general system-design perspective. The authors suggest the concept of a neural gate which is similar to the processing element in an artificial neural system but generalized into handling various types of information such as fuzzy logic, probabilistic, and Boolean information combined. Forecasting of stock market returns, assessment of country risk, and rating of stocks based on fuzzy rules, probabilistic, and Boolean data are areas where systems using these neural gates may be applied. A database containing about 800 sets of company data for the preceding three years where each set represents one stock was used to test the intelligent stock selection system considered.<<ETX>>