DocumentCode :
1927952
Title :
A New Fuzzy Time-Series Based on Two Factors to Predict Taiex
Author :
Cheng, Ching-Hsue ; Chen, Tai-Liang ; Huang, Chen-Chi
Author_Institution :
Nat. Yunlin Univ. of Sci. & Technol., Taipei
Volume :
3
fYear :
2007
fDate :
19-22 Aug. 2007
Firstpage :
1365
Lastpage :
1370
Abstract :
In stock markets, many factors such as financial reports, market news and technical analysis indicators are considered to influence stock price. In this paper, we propose a new fuzzy time-series model employing two factors (stock price and a technical analysis indicator of trading volume) to forecast stock index. In this paper, we employ actual trading data of Taiwan stock index (TAIEX) as experimental dataset and two multiple-factor fuzzy time-series models, Chen´s (2000) and Huarng´s (2005), as comparison models. The experimental results indicate that our model outperforms the listing models.
Keywords :
forecasting theory; fuzzy set theory; stock markets; time series; TAIEX; Taiwan stock index; multiple-factor fuzzy time-series models; stock index forecasting; stock markets; stock price; technical analysis indicator; trading volume; Cybernetics; Information management; Information science; Machine learning; Mathematics; Stock markets; Fuzzy linguistic variable; Fuzzy time-series Model; forecasting TAIEX;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics, 2007 International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-0973-0
Electronic_ISBN :
978-1-4244-0973-0
Type :
conf
DOI :
10.1109/ICMLC.2007.4370357
Filename :
4370357
Link To Document :
بازگشت