Title :
A genetic fuzzy expert system for stock market timing
Author_Institution :
Sch. of Bus. & Adm., Open Univ. of Hong Kong, Kowloon, China
Abstract :
Buying and selling of stocks is an essential activity in financial markets. Financial experts invented many market indicators to monitor the movement of stock prices. Trading rules were defined on these indicators for generating buy-sell signals. These rules are fuzzy in nature and they can predict to a certain extent but not always the price movement of stocks. Their accuracy is time-varying and it is impossible to have the best trading rule. A certain combination of trading rules will generate more reliable buy-sell signals for a particular stock in a certain period of time. The selection of these trading rules can be formulated as an optimization problem. We propose a new stock market timing system by integrating a genetic algorithm with a fuzzy expert system. A genetic algorithm is used to optimize the selection of fuzzy trading rules. Experiments were conducted to evaluate the performance of the system and the results indicate that the system can generate more reliable buy-sell signals even in a declining market
Keywords :
expert systems; financial data processing; fuzzy logic; genetic algorithms; stock markets; uncertainty handling; experiments; financial markets; financial trading rules; genetic algorithm; genetic fuzzy expert system; optimization; stock market timing; stock prices; Art; Data mining; Fuzzy logic; Genetic algorithms; Humans; Hybrid intelligent systems; Monitoring; Signal generators; Stock markets; Timing;
Conference_Titel :
Evolutionary Computation, 2001. Proceedings of the 2001 Congress on
Conference_Location :
Seoul
Print_ISBN :
0-7803-6657-3
DOI :
10.1109/CEC.2001.934420
