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

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 g...

Full description

Saved in:
Bibliographic Details
Main Authors: Chueh-Yung Tsao, Shu-Heng Chen
Format: Conference Proceeding
Language:English
Subjects:
Econometrics
Economic forecasting
Finance
Pattern analysis
Pattern recognition
Self organizing feature maps
Signal analysis
Signal detection
Testing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
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.
DOI:10.1109/CIFER.2003.1196286