A novel stock forecasting model based on fuzzy time series and genetic algorithm

Stock market has been developed for over twenty years, and has gone deeply into all aspects of daily economic life and attracted more and more investors' attentions. Therefore, researches on finding internal rules and establishing an efficient stock forecast model to help investors minimize risks and maximize returns are very practical and amazing. In this paper, a hybrid model FTSGA based on fuzzy time series and genetic algorithm is proposed. FTSGA improves the performance by applying the operations of genetic algorithm such as selection, crossover and mutation to iteratively search a good discourse partition. TAIEX is selected as the experimental data set. And experimental results show that comparing with other models based on fuzzy time series FTSGA can greatly reduce the root mean square error and improve accuracy.