Self-organizing maps as a foundation for charting or geometric pattern recognition in financial time series

Title	Self-organizing maps as a foundation for charting or geometric pattern recognition in financial time series
Creator	Chen, Shu-heng;Tsao, Chueh-Yung 陳樹衡
Contributor	經濟系
Date	2003
Date Issued	11-May-2015 11:48:06 (UTC+8)
Summary	For a long time technical analysts have detected trading signals with charts. Nonetheless, from a scientific viewpoint, charts are somewhat subjective objects. Using Kohonen`s self-organizing maps (SOMs), the research presented proposes a systematic and automatic approach to charting, or more generally stated, geometric pattern recognition. It is found that the charts discovered using SOM in empirical time series do transmit useful information, and that it is hard for such information to be captured by ordinary econometric methods.
Relation	Computational Intelligence for Financial Engineering, 2003. Proceedings. 2003 IEEE International Conference on 20-23 March 2003, Page(s): 387 - 394
Type	conference
DOI	http://dx.doi.org/10.1109/CIFER.2003.1196286

dc.contributor	經濟系
dc.creator (作者)	Chen, Shu-heng;Tsao, Chueh-Yung
dc.creator (作者)	陳樹衡	zh_TW
dc.date (日期)	2003
dc.date.accessioned	11-May-2015 11:48:06 (UTC+8)	-
dc.date.available	11-May-2015 11:48:06 (UTC+8)	-
dc.date.issued (上傳時間)	11-May-2015 11:48:06 (UTC+8)	-
dc.identifier.uri (URI)	http://nccur.lib.nccu.edu.tw/handle/140.119/75064	-
dc.description.abstract (摘要)	For a long time technical analysts have detected trading signals with charts. Nonetheless, from a scientific viewpoint, charts are somewhat subjective objects. Using Kohonen`s self-organizing maps (SOMs), the research presented proposes a systematic and automatic approach to charting, or more generally stated, geometric pattern recognition. It is found that the charts discovered using SOM in empirical time series do transmit useful information, and that it is hard for such information to be captured by ordinary econometric methods.
dc.format.extent	130 bytes	-
dc.format.mimetype	text/html	-
dc.relation (關聯)	Computational Intelligence for Financial Engineering, 2003. Proceedings. 2003 IEEE International Conference on 20-23 March 2003, Page(s): 387 - 394
dc.title (題名)	Self-organizing maps as a foundation for charting or geometric pattern recognition in financial time series
dc.type (資料類型)	conference	en
dc.identifier.doi (DOI)	10.1109/CIFER.2003.1196286
dc.doi.uri (DOI)	http://dx.doi.org/10.1109/CIFER.2003.1196286